© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71386
    Prev
    Next
    INDEX
    Explanations

    `id`, `essential`, `critical`, `largest` identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
     narcot
    0.46
     oppress
    0.44
     朱
    0.44
     Decedent
    0.42
    angerschaft
    0.42
    Encryption
    0.42
    صحاب
    0.42
     adhipp
    0.42
     अभियुक्त
    0.42
     tetrach
    0.41
    POSITIVE LOGITS
    тные
    0.41
    €
    0.41
     travels
    0.39
     последние
    0.38
     വിദ
    0.38
    ึ
    0.38
    га
    0.37
    繁
    0.37
     inconvenient
    0.37
    があれば
    0.37
    Activations Density 0.001%

    No Known Activations