© 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. 87384
    Prev
    Next
    INDEX
    Explanations

    by

    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
    </h2>
    -1.94
     '
    -1.69
    rénées
    -1.65
     existem
    -1.63
     asses
    -1.61
     jego
    -1.60
     
    -1.57
    関する
    -1.55
     íntegra
    -1.54
     mastery
    -1.52
    POSITIVE LOGITS
     by
    3.17
     virtue
    2.28
     a
    2.13
     the
    2.03
    ቍ
    1.95
     توسط
    1.94
     our
    1.88
     an
    1.84
    by
    1.84
     oleh
    1.83
    Activations Density 0.287%

    No Known Activations