© 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. 22-GEMMASCOPE-RES-131K
    7. 71285
    Prev
    Next
    INDEX
    Explanations

    text separated by delimiters

    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_22/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
    grains
    -1.11
     trouve
    -1.06
    fundo
    -1.05
     todas
    -1.02
     cí
    -0.95
     schop
    -0.92
     dam
    -0.91
    enges
    -0.90
    してくれた
    -0.90
     mostra
    -0.90
    POSITIVE LOGITS
     between
    1.61
     между
    1.46
    between
    1.27
    étricas
    1.09
    ários
    1.07
    rigated
    1.05
    Between
    1.04
     خریدار
    1.02
    <bos>
    1.01
     結婚
    0.99
    Activations Density 0.025%

    No Known Activations