© 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. 12-GEMMASCOPE-2-RES-16K
    7. 7898
    Prev
    Next
    INDEX
    Explanations

    installing torchvision

    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_12_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
    osexual
    1.43
     Karam
    1.16
    踟
    1.12
    เค
    1.12
    hetamine
    1.09
    osexuality
    1.09
    namefont
    1.09
    SOI
    1.08
     hermaph
    1.07
    Comparator
    1.07
    POSITIVE LOGITS
    лина
    1.61
     from
    1.55
     Chain
    1.52
    靭
    1.52
     pockets
    1.49
     into
    1.49
     peak
    1.48
     web
    1.45
     special
    1.43
     apron
    1.41
    Activations Density 0.003%

    No Known Activations