© 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. 148969
    Prev
    Next
    INDEX
    Explanations

    lists and bullet points

    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
    얻
    0.71
     Peer
    0.70
     얻
    0.70
    Reco
    0.69
    Infer
    0.69
    ണിയ
    0.68
    ్యంలో
    0.68
    AddNew
    0.67
    GetData
    0.67
    ிகள்
    0.66
    POSITIVE LOGITS
    dl
    0.68
     ইন্দুর
    0.61
    strategic
    0.60
     shock
    0.60
    dib
    0.60
    որ
    0.60
    ാ
    0.59
     उतर
    0.59
    ल्ड
    0.59
    qr
    0.58
    Activations Density 0.001%

    No Known Activations