© 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. 34-GEMMASCOPE-RES-131K
    7. 78777
    Prev
    Next
    INDEX
    Explanations

    question/answer formats

    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
     كور
    -0.81
     قهر
    -0.78
    無事に
    -0.77
    стреча
    -0.76
    Tues
    -0.75
    rano
    -0.74
    エール
    -0.73
    なければならない
    -0.73
     Chao
    -0.71
    ötet
    -0.70
    POSITIVE LOGITS
    deselect
    0.88
    бом
    0.84
    ATURE
    0.82
     TODO
    0.81
     eclipse
    0.79
    Around
    0.79
    peek
    0.78
    VAO
    0.77
    中秋
    0.77
     here
    0.77
    Activations Density 0.017%

    No Known Activations