© 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. 79125
    Prev
    Next
    INDEX
    Explanations

    ToolBar button labels

    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
    ⵔ
    -0.86
     invertir
    -0.81
    HV
    -0.81
     urządzenia
    -0.80
    Employee
    -0.79
     سبورت
    -0.78
     klaar
    -0.78
    Spect
    -0.77
    ervos
    -0.77
     작성
    -0.76
    POSITIVE LOGITS
     erlang
    0.72
    尤其
    0.71
    ⇰
    0.69
    癣
    0.69
     volcán
    0.69
     conserved
    0.69
     sven
    0.69
     Asbury
    0.68
    无限
    0.68
     Australian
    0.68
    Activations Density 0.018%

    No Known Activations