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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 786
    Prev
    Next
    INDEX
    Explanations

    asking for roles and names

    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_29_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
    Su
    0.73
     invit
    0.70
    SU
    0.69
     convid
    0.67
     teatral
    0.67
    MPa
    0.66
    °.
    0.66
    ⁷
    0.65
     coincide
    0.65
     zonal
    0.64
    POSITIVE LOGITS
     Constantine
    0.59
    కోవడం
    0.58
     perhitungan
    0.57
     Calculations
    0.57
    ޮ
    0.57
    計算
    0.56
    氨
    0.55
     оружи
    0.54
    建築
    0.54
    ている
    0.54
    Activations Density 0.014%

    No Known Activations