© 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. 75170
    Prev
    Next
    INDEX
    Explanations

    gives you

    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
     it
    -3.08
     they
    -2.63
    because
    -2.20
     there
    -2.16
     by
    -1.88
     you
    -1.80
     они
    -1.74
     Nationen
    -1.73
     on
    -1.70
     these
    -1.70
    POSITIVE LOGITS
    愎
    1.93
     andere
    1.88
     semelh
    1.84
    を使用した
    1.79
     incapa
    1.71
     a
    1.71
    苤
    1.68
    ︲
    1.67
     impuls
    1.66
     consente
    1.63
    Activations Density 0.016%

    No Known Activations