© 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. 112570
    Prev
    Next
    INDEX
    Explanations

    names in citations

    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
     numerosas
    -1.89
     numerosos
    -1.80
     mencionado
    -1.79
     erfolgre
    -1.73
     sonrası
    -1.71
     außergewöhn
    -1.63
     beliebt
    -1.63
     personalizar
    -1.62
     zufried
    -1.57
     time
    -1.56
    POSITIVE LOGITS
    。
    1.82
    G
    1.71
    Z
    1.70
    U
    1.66
     who
    1.65
    THING
    1.60
    “,
    1.55
     incess
    1.54
    B
    1.54
    ли
    1.52
    Activations Density 0.002%

    No Known Activations