© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65595
    Prev
    Next
    INDEX
    Explanations

    aliased identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ğinde
    -0.89
     posición
    -0.88
    levard
    -0.88
     technisch
    -0.88
     épreuves
    -0.87
     praktisch
    -0.87
    ㎍
    -0.87
     katze
    -0.87
    能不能
    -0.86
     kapturem
    -0.85
    POSITIVE LOGITS
     tmp
    0.92
    その時
    0.85
    先代
    0.84
     sehr
    0.83
     hopefully
    0.82
     that
    0.82
     ________
    0.82
     _______
    0.82
     suç
    0.81
     ______
    0.80
    Activations Density 0.084%

    No Known Activations