© 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. 118899
    Prev
    Next
    INDEX
    Explanations

    Copyright ©

    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
     gastronomía
    -1.76
     vegetación
    -1.66
     almohada
    -1.65
     esquí
    -1.63
     their
    -1.59
     během
    -1.56
     hierba
    -1.52
     sends
    -1.52
     heuti
    -1.43
     maquillaje
    -1.42
    POSITIVE LOGITS
    Although
    1.86
    Regardless
    1.68
    Following
    1.66
    اااا
    1.64
    Several
    1.63
    Perhaps
    1.60
    Another
    1.60
    although
    1.59
    Whether
    1.59
    Nearly
    1.57
    Activations Density 0.035%

    No Known Activations