© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 40412
    Prev
    Next
    INDEX
    Explanations

    unknown or unexplained phenomenon

    np_acts-logits-general · gemini-2.5-flash-lite

    descriptions of physical properties, characteristics, or attributes of objects and entities.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jamesnaruto04

    Tokens that are parts of direct objects or complements following verbs, prepositions, or copulas, particularly in contexts where they complete the meaning of a predicate or describe what is being acted upon, observed, or discussed.

    eleuther_acts_top20 · claude-4-5-sonnetTriggered by @jamesnaruto04
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Normally
    0.61
     normally
    0.53
     Normally
    0.53
    normally
    0.50
     overuse
    0.41
    Traditionally
    0.41
    囉
    0.40
    姦
    0.40
    分手
    0.40
    平时
    0.39
    POSITIVE LOGITS
     mysterious
    1.20
     unidentified
    1.19
     unknown
    1.01
     mystery
    0.98
     myster
    0.97
     unexplained
    0.91
     enigmatic
    0.91
     непоня
    0.90
    Unknown
    0.89
     Mysterious
    0.89
    Activations Density 0.187%

    No Known Activations