© 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. 34-GEMMASCOPE-RES-131K
    7. 77412
    Prev
    Next
    INDEX
    Explanations

    file, License, COPYRIGHT

    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_34/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
    umine
    -0.74
    Tun
    -0.70
     túnel
    -0.69
     fábrica
    -0.69
     paredes
    -0.69
     perdido
    -0.68
     Polizei
    -0.67
     Mattress
    -0.67
    oldValue
    -0.66
    ㅋㅋ
    -0.66
    POSITIVE LOGITS
     합니다
    0.82
     florida
    0.79
     تج
    0.74
    split
    0.73
    Start
    0.71
    anneer
    0.71
     مرد
    0.69
    agara
    0.68
    start
    0.68
    œur
    0.67
    Activations Density 0.080%

    No Known Activations