© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130431
    Prev
    Next
    INDEX
    Explanations

    code delimiters and start tokens

    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
    mle
    -0.85
     cepillo
    -0.84
     kuu
    -0.83
    émie
    -0.83
    ignée
    -0.82
    狡
    -0.82
    daya
    -0.81
    tribe
    -0.81
     desempen
    -0.81
     madman
    -0.79
    POSITIVE LOGITS
    しない
    0.95
     anfangen
    0.89
    خواندن
    0.85
     begin
    0.85
     berätt
    0.83
     for
    0.83
    还不错
    0.82
     it
    0.81
     zač
    0.81
     tenga
    0.80
    Activations Density 0.002%

    No Known Activations