© 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. 104922
    Prev
    Next
    INDEX
    Explanations

    Notably, it is

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

    used with existing layers

    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
    Knowing
    0.50
    ステー
    0.48
     since
    0.47
     decompression
    0.46
     capturing
    0.46
     informativa
    0.43
    .${
    0.43
     correcting
    0.43
    ²,
    0.42
    रियो
    0.41
    POSITIVE LOGITS
     szabad
    0.44
    ValMap
    0.41
    olées
    0.41
    üğ
    0.41
     ebenfalls
    0.40
    alnız
    0.40
     Pathol
    0.40
     Dye
    0.40
    MediaPath
    0.40
    ilmiştir
    0.40
    Activations Density 0.000%

    No Known Activations