© 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-65K
    7. 11516
    Prev
    Next
    INDEX
    Explanations

    numbers followed by million or currency

    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_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
     co
    0.41
     Pel
    0.41
     Chem
    0.40
    C
    0.38
     pasting
    0.37
     Vel
    0.36
    ofd
    0.36
     Poet
    0.36
     surface
    0.36
    Audio
    0.36
    POSITIVE LOGITS
     jasa
    0.45
     andolan
    0.44
     huidige
    0.41
     بلکہ
    0.40
     fomentar
    0.40
    haman
    0.40
     financiar
    0.40
    窯
    0.40
     služ
    0.39
    দেশিক
    0.39
    Activations Density 0.022%

    No Known Activations