© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 50185
    Prev
    Next
    INDEX
    Explanations

    Google API authorization

    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
    ménage
    -0.85
    ahy
    -0.81
    phazard
    -0.79
     gewesen
    -0.79
    occuper
    -0.77
    ghis
    -0.74
    vick
    -0.73
    の方も
    -0.72
    OnClick
    -0.71
     nazwis
    -0.71
    POSITIVE LOGITS
    GOOGLE
    0.88
    refresh
    0.85
     GOOGLE
    0.80
     firefighters
    0.80
    JsonKey
    0.79
    ouwd
    0.78
     metadata
    0.75
     infan
    0.72
     Metadata
    0.72
     Vodka
    0.71
    Activations Density 0.046%

    No Known Activations