© 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. 38719
    Prev
    Next
    INDEX
    Explanations

    honoring people and events

    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
    稣
    -2.30
     caters
    -1.87
    鼉
    -1.79
     ними
    -1.77
     ";
    -1.73
     constantemente
    -1.72
    cahontas
    -1.72
     freaking
    -1.71
     них
    -1.70
    龘
    -1.70
    POSITIVE LOGITS
    We
    2.22
    ably
    2.16
     eviden
    1.95
     of
    1.88
     Saltar
    1.87
     這
    1.76
    庒
    1.75
     monstru
    1.74
    ائم
    1.71
    </b>
    1.70
    Activations Density 0.007%

    No Known Activations