© 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. 28474
    Prev
    Next
    INDEX
    Explanations

    programming variables

    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
     tetapi
    -1.75
    .
    -1.73
     colaborar
    -1.72
     típica
    -1.68
     adecuada
    -1.66
     コスプレ
    -1.61
     MUCH
    -1.60
    the
    -1.59
     aclarar
    -1.57
    there
    -1.56
    POSITIVE LOGITS
    ?"
    2.50
    新款
    1.68
    白衣
    1.68
    砰
    1.68
    精品
    1.66
     was
    1.64
    !"
    1.59
     fier
    1.59
    毟
    1.58
     عمومی
    1.57
    Activations Density 0.024%

    No Known Activations