© 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. 10-GEMMASCOPE-RES-131K
    7. 70730
    Prev
    Next
    INDEX
    Explanations

    action or operation

    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_10/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
    殃
    -1.57
    顔を
    -1.54
    }
    -1.49
    -
    -1.48
     yaptığı
    -1.46
     peně
    -1.41
     amd
    -1.41
     pourtant
    -1.41
     обви
    -1.38
    がありますが
    -1.38
    POSITIVE LOGITS
    не
    1.78
    Not
    1.71
     Not
    1.57
    0
    1.56
     For
    1.55
     by
    1.53
    ："
    1.52
     мен
    1.48
     more
    1.48
     new
    1.45
    Activations Density 0.079%

    No Known Activations