© 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. 103389
    Prev
    Next
    INDEX
    Explanations

    HTML head sections

    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
     ところ
    -0.79
    gies
    -0.76
    嚴重
    -0.75
     viciss
    -0.74
     confe
    -0.73
     unfavorable
    -0.72
     dimensi
    -0.71
    میل
    -0.71
     blackberry
    -0.70
     Quid
    -0.70
    POSITIVE LOGITS
     spannend
    0.89
    OPSIS
    0.86
     estándares
    0.86
    MessageInfo
    0.84
    Resumen
    0.84
    四方
    0.82
    essages
    0.81
     tt
    0.80
    ogramm
    0.79
    artige
    0.78
    Activations Density 0.002%

    No Known Activations