© 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. 6967
    Prev
    Next
    INDEX
    Explanations

    word followed by and

    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
    -/
    1.13
    /
    0.97
    気軽に
    0.95
    wxr
    0.94
     Gettysburg
    0.94
    いたり
    0.92
    otho
    0.91
    velt
    0.90
    本社
    0.89
     pyaar
    0.89
    POSITIVE LOGITS
    ؟
    1.54
     Algar
    1.53
     arid
    1.51
     нуле
    1.42
    ancher
    1.38
     ссылка
    1.37
     последние
    1.37
    ណ៍
    1.37
    ილები
    1.36
     عقد
    1.36
    Activations Density 0.059%

    No Known Activations