© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76627
    Prev
    Next
    INDEX
    Explanations

    Indian names and places

    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
     Larsen
    -0.80
     hardships
    -0.71
    の原因
    -0.67
    hark
    -0.67
    元年
    -0.65
     Ambiente
    -0.65
     warunki
    -0.64
     Thurston
    -0.63
     viewport
    -0.63
    FieldName
    -0.63
    POSITIVE LOGITS
    maxX
    0.81
    volezza
    0.81
    ارية
    0.77
    뿔
    0.75
    Aval
    0.74
     Bundestag
    0.73
    bookstore
    0.73
    gameId
    0.73
     Gastro
    0.72
    aval
    0.70
    Activations Density 0.045%

    No Known Activations