Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 3858
    Prev
    Next
    INDEX
    Explanations

    predicting punctuation and next words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     chiế
    0.74
     bukan
    0.73
    崖
    0.72
    ScriptInterface
    0.72
     deseos
    0.72
    呼び
    0.72
     زنان
    0.72
     Overs
    0.71
     Shank
    0.70
     waved
    0.70
    POSITIVE LOGITS
    <th>
    0.78
     wynika
    0.68
    டன
    0.67
    ően
    0.66
     দুদকের
    0.66
    有一些
    0.65
    जेदार
    0.65
    metics
    0.64
    CHR
    0.64
     মানববন্ধন
    0.63
    Activations Density 0.014%

    No Known Activations