© 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. 31928
    Prev
    Next
    INDEX
    Explanations

    HTML metadata and code configuration

    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
    PSS
    -0.79
     Override
    -0.77
    섰
    -0.71
     Filling
    -0.71
     FILL
    -0.69
    ganz
    -0.69
     zkou
    -0.68
    Wrapped
    -0.68
    estación
    -0.68
     uží
    -0.67
    POSITIVE LOGITS
     completes
    0.75
     ДТП
    0.65
    onation
    0.63
    ча
    0.63
     sze
    0.61
     перене
    0.61
    INAL
    0.60
    พร
    0.60
     spam
    0.60
     présente
    0.59
    Activations Density 0.098%

    No Known Activations