© 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. 4700
    Prev
    Next
    INDEX
    Explanations

    institutional, individual, donors

    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
    maire
    2.85
    ך
    2.73
     puj
    2.63
    スル
    2.63
    storms
    2.62
    nae
    2.60
    ياء
    2.57
    ska
    2.57
    าง
    2.55
    зова
    2.50
    POSITIVE LOGITS
    o
    1.68
    geteilt
    1.39
     private
    1.37
    e
    1.37
    walled
    1.31
    a
    1.30
    ccin
    1.28
     prywat
    1.28
    (":")[
    1.26
     individual
    1.26
    Activations Density 0.006%

    No Known Activations