© 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. 107676
    Prev
    Next
    INDEX
    Explanations

    type: :feature, :graphql

    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
    ardon
    -0.78
    yethylene
    -0.78
    chom
    -0.74
    ēja
    -0.73
     Sodium
    -0.73
     audiencia
    -0.70
     دولار
    -0.70
    ZZLE
    -0.69
    manos
    -0.69
     Fulton
    -0.68
    POSITIVE LOGITS
     upacara
    0.71
    anı
    0.68
    Gameplay
    0.68
    鞘
    0.67
     Tia
    0.66
    verk
    0.66
    sional
    0.63
    tables
    0.62
     tables
    0.61
    venty
    0.60
    Activations Density 0.058%

    No Known Activations