© 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. 66049
    Prev
    Next
    INDEX
    Explanations

    Q A questions

    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
     سایز
    -0.80
     colina
    -0.77
    thral
    -0.75
     isEqualToString
    -0.75
    opre
    -0.75
    IBAN
    -0.73
    ahuje
    -0.71
     imgur
    -0.71
     होना
    -0.70
    iela
    -0.70
    POSITIVE LOGITS
     margin
    0.91
     margins
    0.84
     situation
    0.79
     situações
    0.75
     Miss
    0.75
    margins
    0.74
    这些人
    0.74
    Sera
    0.74
    margin
    0.73
     escolh
    0.73
    Activations Density 0.000%

    No Known Activations