© 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. 159738
    Prev
    Next
    INDEX
    Explanations

    list item markers

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

    quote mark followed by word

    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
     PBL
    0.50
     minorities
    0.48
    ième
    0.47
     newcomers
    0.47
     questioning
    0.45
    新
    0.45
     Highways
    0.45
     sidelined
    0.44
     अलै
    0.44
     hijacking
    0.44
    POSITIVE LOGITS
    醫師
    0.45
    ילו
    0.44
    ScriptObject
    0.44
    駱
    0.43
    optimizer
    0.43
    复制代码
    0.41
     deset
    0.40
    Coluna
    0.40
     Omaha
    0.39
    駝
    0.39
    Activations Density 0.000%

    No Known Activations