© 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. 48865
    Prev
    Next
    INDEX
    Explanations

    businesses, security, option, length, Written

    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
    agami
    -0.75
     χρη
    -0.72
    enab
    -0.69
    зка
    -0.67
    Alerter
    -0.66
    Carsten
    -0.66
    Pry
    -0.65
    Fay
    -0.65
     yanında
    -0.65
     tolerant
    -0.64
    POSITIVE LOGITS
     дел
    0.71
    ⇝
    0.68
    Win
    0.68
    bona
    0.66
    assertFalse
    0.65
     Dü
    0.65
    COLUMN
    0.64
    statusCode
    0.64
     insidious
    0.63
    愕
    0.62
    Activations Density 0.054%

    No Known Activations