© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 80767
    Prev
    Next
    INDEX
    Explanations

    license or legal citation

    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
    nutrition
    -0.86
     Recife
    -0.85
     ốp
    -0.79
    istern
    -0.78
     kirke
    -0.76
     egne
    -0.76
     глазах
    -0.76
    ostruct
    -0.75
     freundlich
    -0.75
     stål
    -0.75
    POSITIVE LOGITS
     compared
    0.90
     hash
    0.88
    GetHashCode
    0.86
    hash
    0.82
    hashCode
    0.82
    Preparazione
    0.82
    hynchus
    0.81
    viez
    0.79
     hashCode
    0.79
    cinating
    0.78
    Activations Density 0.000%

    No Known Activations