© 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. 158116
    Prev
    Next
    INDEX
    Explanations

    year and fourth

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

    explanation is often

    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
    sf
    0.49
    nak
    0.49
    fs
    0.48
    ->
    0.44
    Head
    0.44
    !}
    0.43
    imų
    0.43
     Head
    0.42
    ].
    0.42
    $,
    0.42
    POSITIVE LOGITS
    成长
    0.47
    养老
    0.46
    动力
    0.46
    设定
    0.45
     друго
    0.45
    olução
    0.45
    льта
    0.43
    步伐
    0.43
    ئن
    0.43
    StudentID
    0.43
    Activations Density 0.001%

    No Known Activations