© 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. 69251
    Prev
    Next
    INDEX
    Explanations

    comparison using over

    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
     then
    -2.17
    </h2>
    -1.59
     there
    -1.43
     entonces
    -1.38
     Direktur
    -1.34
    </blockquote>
    -1.33
    咐
    -1.30
     changed
    -1.28
     got
    -1.27
     is
    -1.27
    POSITIVE LOGITS
    vlád
    1.86
     It
    1.85
    jednoc
    1.75
     the
    1.64
     usual
    1.63
    ⸂
    1.63
    indelijk
    1.60
     okno
    1.57
     zask
    1.57
     öv
    1.56
    Activations Density 0.027%

    No Known Activations