© 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. 237276
    Prev
    Next
    INDEX
    Explanations

    as of date or time

    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
     beheld
    0.51
    ತಿ
    0.50
     judgments
    0.46
     dilihat
    0.45
     judgements
    0.45
    .(\
    0.45
     in
    0.44
    .$,
    0.43
     inlaid
    0.43
     carinatis
    0.43
    POSITIVE LOGITS
    湄
    0.49
    控え
    0.47
    ë
    0.45
     Placeholder
    0.45
     Succession
    0.45
     Aceh
    0.44
     Seville
    0.44
    islang
    0.44
     Seigneur
    0.44
     Athens
    0.44
    Activations Density 0.005%

    No Known Activations