© 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-262K
    4. 143618
    Prev
    Next
    INDEX
    Explanations

    protobuf, actually, communist, rule, direction, organized

    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
    PROTE
    0.43
    IGATION
    0.42
     receivables
    0.40
     fueron
    0.40
     १९
    0.40
    寶
    0.39
     copper
    0.39
    仍
    0.39
    ADMIN
    0.39
     footh
    0.39
    POSITIVE LOGITS
    ään
    0.45
    ären
    0.44
    *,
    0.44
    essive
    0.43
    ğın
    0.43
    相对于
    0.43
    (),
    0.42
    વિધ
    0.42
    𝓲
    0.42
    *(
    0.42
    Activations Density 0.006%

    No Known Activations