© 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. 108380
    Prev
    Next
    INDEX
    Explanations

    data recorders, listening, see

    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
     unsightly
    0.47
     ugl
    0.45
    最近
    0.43
     indigestion
    0.41
     glamorous
    0.41
    ディション
    0.41
     robbers
    0.41
    ＊
    0.40
     ಒಳಗ
    0.40
     mysterious
    0.40
    POSITIVE LOGITS
     Elected
    0.46
    arı
    0.45
    UIServer
    0.44
    bė
    0.43
    aru
    0.43
     оси
    0.42
    ̦
    0.42
     {
    0.42
     нейтро
    0.42
    ͕
    0.42
    Activations Density 0.010%

    No Known Activations