© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4266
    Prev
    Next
    INDEX
    Explanations

    WinError, hypnotherapist, pawscuse, personalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    ＰＥＮＡＮＡ
    2.77
     Wies
    2.70
    ティブ
    2.68
     ular
    2.57
    缤
    2.55
    lovl
    2.55
    参数向量
    2.54
    ologi
    2.53
     GUS
    2.52
     interag
    2.52
    POSITIVE LOGITS
    ă
    1.02
    a
    0.95
    e
    0.93
    ö
    0.79
    s
    0.74
    t
    0.70
    ｏ
    0.54
    organised
    0.50
     sufferer
    0.49
    añ
    0.48
    Activations Density 0.010%

    No Known Activations