© 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. 7893
    Prev
    Next
    INDEX
    Explanations

    here to help

    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
    んばんは
    2.01
    Classic
    1.97
    keySet
    1.96
    akarta
    1.96
    стное
    1.94
     Range
    1.94
    恕
    1.93
     carrière
    1.92
    стная
    1.91
    翌
    1.89
    POSITIVE LOGITS
    encial
    1.55
    ential
    1.32
    standing
    1.31
    lemm
    1.29
    eing
    1.28
    silyl
    1.23
    enced
    1.18
    percaya
    1.13
    áték
    1.10
    rums
    1.09
    Activations Density 0.062%

    No Known Activations