© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 149507
    Prev
    Next
    INDEX
    Explanations

    what you want

    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
     Antennes
    0.73
     equipos
    0.72
     jawaban
    0.70
    ፣
    0.69
    akaian
    0.69
     tamen
    0.67
     accesorios
    0.67
     binatang
    0.67
     homenagem
    0.67
     Nationen
    0.67
    POSITIVE LOGITS
     lot
    0.69
     […]
    0.67
    specific
    0.58
     tend
    0.57
     uncomfortable
    0.57
    lot
    0.56
    Why
    0.56
     unsightly
    0.56
    <unused2222>
    0.54
     됐
    0.54
    Activations Density 0.004%

    No Known Activations