© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113427
    Prev
    Next
    INDEX
    Explanations

    command line arguments

    np_acts-logits-general · gemini-2.5-flash-lite

    command-line flags and options (single-letter arguments preceded by a dash).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    嘥
    -2.19
     ‌
    -2.09
     моя
    -2.05
    л
    -1.91
    獓
    -1.89
     vinculados
    -1.78
    
    -1.76
     sebagainya
    -1.76
     $^{
    -1.71
    几人
    -1.68
    POSITIVE LOGITS
     are
    2.20
     -
    2.13
     These
    1.91
    </b>
    1.88
     for
    1.85
     a
    1.78
    痒
    1.77
     From
    1.72
    的作用
    1.70
     including
    1.69
    Activations Density 0.024%

    No Known Activations