© 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. 58618
    Prev
    Next
    INDEX
    Explanations

    released under

    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
     tells
    -1.05
     promotes
    -0.82
     Balzac
    -0.79
     repente
    -0.78
    vz
    -0.78
     bijou
    -0.78
     encourages
    -0.78
     Simeon
    -0.77
     شیشه
    -0.77
     sings
    -0.77
    POSITIVE LOGITS
     lienzo
    0.82
     Karnataka
    0.81
     более
    0.78
     Kod
    0.77
    ERALD
    0.75
    Kod
    0.73
    tholes
    0.73
     REALLY
    0.73
     Ababa
    0.72
    meisterschaften
    0.72
    Activations Density 0.001%

    No Known Activations