© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45360
    Prev
    Next
    INDEX
    Explanations

    kind of

    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
    踯
    -2.08
    </b>
    -1.84
    たった
    -1.77
     cambiando
    -1.73
     you
    -1.70
    乚
    -1.70
    却不
    -1.68
    栳
    -1.61
    鶺
    -1.59
     htt
    -1.58
    POSITIVE LOGITS
    ';
    1.95
     an
    1.94
     a
    1.84
    ")
    1.77
    ')
    1.75
     at
    1.74
    山西
    1.74
     had
    1.69
    </h3>
    1.67
     as
    1.67
    Activations Density 0.013%

    No Known Activations