© 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. 129059
    Prev
    Next
    INDEX
    Explanations

    foreign and code snippets

    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
    ͌
    -1.04
     podczas
    -1.03
     berkaitan
    -1.02
    ultier
    -1.00
     menggunakan
    -0.99
     Krise
    -0.98
    ^{\
    -0.96
    産の
    -0.93
    offrir
    -0.91
    MockMvc
    -0.90
    POSITIVE LOGITS
    ないけど
    1.02
     kuu
    0.95
    octobre
    0.88
     ergänzt
    0.88
    に行きました
    0.87
     kaas
    0.86
     jät
    0.86
     Boats
    0.84
     封面
    0.84
     fordern
    0.82
    Activations Density 0.034%

    No Known Activations