© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63732
    Prev
    Next
    INDEX
    Explanations

    cold storage

    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
     impug
    -0.81
     shifting
    -0.79
    gas
    -0.77
    Packs
    -0.76
    덟
    -0.75
     کیلو
    -0.74
     fueran
    -0.73
    地说
    -0.73
    各種
    -0.73
    各种
    -0.73
    POSITIVE LOGITS
    ocean
    0.90
    ต่อ
    0.88
     geboren
    0.85
     Metab
    0.84
     délais
    0.80
    rensa
    0.80
    billon
    0.80
     brachten
    0.79
     Entomol
    0.79
    DECREF
    0.79
    Activations Density 0.000%

    No Known Activations