© 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. 26039
    Prev
    Next
    INDEX
    Explanations

    to all or you

    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
    ’
    0.54
    /
    0.53
     Ada
    0.47
     или
    0.46
     கூடிய
    0.46
     hoặc
    0.46
     jede
    0.46
     aby
    0.45
     আপনার
    0.45
     вся
    0.45
    POSITIVE LOGITS
     lengthy
    0.47
     Coefficients
    0.47
    ారణ
    0.46
     jabatan
    0.46
    선
    0.46
     participants
    0.46
    癹
    0.46
     proponents
    0.45
     선수
    0.45
     voyageurs
    0.45
    Activations Density 0.006%

    No Known Activations