© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126659
    Prev
    Next
    INDEX
    Explanations

    school courses

    np_acts-logits-general · gemini-2.5-flash-lite

    as of dates and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;
    0.56
     Gaye
    0.49
     Visit
    0.47
     Malhotra
    0.47
     OTP
    0.45
     klicken
    0.45
    ESS
    0.45
     ECM
    0.44
    BB
    0.44
     McGrath
    0.44
    POSITIVE LOGITS
     कस्बे
    0.52
     radicales
    0.47
     kulturn
    0.46
    ▫
    0.46
    सबसे
    0.45
    ક્રિય
    0.45
    んは
    0.44
    tgz
    0.44
    潾
    0.44
     ት
    0.44
    Activations Density 0.000%

    No Known Activations