© 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. 37809
    Prev
    Next
    INDEX
    Explanations

    Community and Q prompts

    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
    𖥸
    -0.91
     waterproof
    -0.83
     detener
    -0.81
    ~*~
    -0.80
    rera
    -0.79
    jake
    -0.78
     fool
    -0.77
    Anwendung
    -0.77
    aguer
    -0.76
    сны
    -0.75
    POSITIVE LOGITS
     womens
    0.96
    interprétation
    0.94
     seksual
    0.90
    IGNORE
    0.85
    leneck
    0.84
     casual
    0.84
     dekol
    0.84
     stille
    0.82
     базо
    0.82
     Womens
    0.81
    Activations Density 0.003%

    No Known Activations