© 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
    5. 15-GEMMASCOPE-2-RES-16K
    7. 1908
    Prev
    Next
    INDEX
    Explanations

    describing systems and their functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
    !!
    2.12
     나의
    2.06
    !!!
    2.06
    !!!!
    1.98
     nostra
    1.98
    %!
    1.98
     nosso
    1.96
    ?!
    1.95
    !!!!!
    1.95
     :).
    1.93
    POSITIVE LOGITS
    
    1.60
     ­
    1.58
    гато
    1.52
    ﹐
    1.51
    rung
    1.51
     ″
    1.47
     Unesco
    1.47
    诌
    1.47
    killers
    1.46
    捱
    1.45
    Activations Density 0.473%

    No Known Activations