© 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. 31887
    Prev
    Next
    INDEX
    Explanations

    technical css and 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
    fia
    -0.77
     INDUSTRIAL
    -0.77
     realizarse
    -0.76
     indústria
    -0.74
     sanitarios
    -0.73
     económicas
    -0.71
     welcomed
    -0.71
     trials
    -0.71
     ancianos
    -0.70
     antigüedad
    -0.70
    POSITIVE LOGITS
    graduates
    0.77
    孫
    0.73
     Cessna
    0.73
    Marshal
    0.72
     bias
    0.71
    Bias
    0.71
    clothes
    0.71
     Crab
    0.71
     Bias
    0.70
    Ward
    0.69
    Activations Density 0.003%

    No Known Activations