© 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. 1713
    Prev
    Next
    INDEX
    Explanations

    perfect + role/purpose

    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
     realizando
    -1.96
    Inggris
    -1.76
    meine
    -1.71
     cewek
    -1.67
     vět
    -1.67
    ейчас
    -1.66
     preparando
    -1.64
    😊
    -1.63
     höl
    -1.61
     ¤
    -1.60
    POSITIVE LOGITS
     thing
    1.74
     a
    1.72
     he
    1.71
     Although
    1.71
     could
    1.68
     Despite
    1.66
     —
    1.64
     did
    1.63
    </h5>
    1.63
     At
    1.61
    Activations Density 0.011%

    No Known Activations