© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43304
    Prev
    Next
    INDEX
    Explanations

    defined constants

    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
    }
    -2.45
     What
    -1.92
    ↵
    -1.88
     Somehow
    -1.74
     There
    -1.66
     Commencez
    -1.63
    低い
    -1.61
    gerton
    -1.59
     cocky
    -1.57
     [
    -1.55
    POSITIVE LOGITS
    隳
    2.11
     Rptr
    1.90
     augusti
    1.86
     that
    1.84
     kuti
    1.71
     personer
    1.71
    豨
    1.71
     grupper
    1.70
    ി
    1.66
     bygge
    1.63
    Activations Density 0.008%

    No Known Activations