© 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. 103329
    Prev
    Next
    INDEX
    Explanations

    copyright notices and licenses

    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
     notori
    -0.90
    rachtet
    -0.90
    onymes
    -0.89
    iak
    -0.87
    μέν
    -0.87
     ensa
    -0.84
    ARKS
    -0.83
    PLAN
    -0.83
    POLICY
    -0.82
    🧮
    -0.81
    POSITIVE LOGITS
    靄
    0.75
     dniu
    0.69
    posx
    0.69
     которого
    0.69
    labelControl
    0.68
     eventually
    0.68
    bop
    0.67
    ーと
    0.66
     examined
    0.66
     dàn
    0.66
    Activations Density 0.091%

    No Known Activations