© 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. 59884
    Prev
    Next
    INDEX
    Explanations

    phrases starting with specific words

    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
     after
    -0.88
     almost
    -0.82
     approximately
    -0.81
     instead
    -0.81
     three
    -0.80
     despite
    -0.79
     nearly
    -0.78
    uevos
    -0.78
     February
    -0.78
     vehemently
    -0.77
    POSITIVE LOGITS
    himself
    1.08
    fre
    0.99
    geren
    0.98
    āja
    0.93
    cein
    0.92
    iços
    0.91
    aso
    0.91
    atious
    0.90
    lení
    0.90
     PPP
    0.90
    Activations Density 0.014%

    No Known Activations