© 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. 14059
    Prev
    Next
    INDEX
    Explanations

    change and comparison

    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
     Likely
    -1.42
     through
    -1.35
    ┙
    -1.34
     Públicas
    -1.33
    ஂ
    -1.31
     This
    -1.31
    difice
    -1.28
    ⅽ
    -1.28
    ᓕ
    -1.27
    هذه
    -1.27
    POSITIVE LOGITS
     than
    2.17
    rasında
    1.73
    什么的
    1.62
     otros
    1.60
     the
    1.58
    >{
    1.53
     otras
    1.52
    </h5>
    1.48
    oping
    1.48
    </h4>
    1.46
    Activations Density 0.014%

    No Known Activations