© 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. 81355
    Prev
    Next
    INDEX
    Explanations

    feature: type

    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
    homem
    -0.74
     deserialize
    -0.71
    買って
    -0.70
    ;'
    -0.69
    cartão
    -0.67
    adine
    -0.65
    amphetamine
    -0.65
     Konzentration
    -0.65
    daya
    -0.65
    wch
    -0.64
    POSITIVE LOGITS
     pipes
    0.77
    πε
    0.74
    логические
    0.73
     Pipes
    0.72
    letti
    0.69
    ZX
    0.68
    解散
    0.68
     magical
    0.66
    клопе
    0.66
     Stirn
    0.66
    Activations Density 0.052%

    No Known Activations