© 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. 84580
    Prev
    Next
    INDEX
    Explanations

    specifies or find

    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
     and
    -2.19
     (
    -1.96
     new
    -1.92
     acknowledged
    -1.64
     adequate
    -1.61
     evidently
    -1.56
     added
    -1.55
     established
    -1.52
     very
    -1.51
     offer
    -1.51
    POSITIVE LOGITS
     écout
    1.96
     dictionnaire
    1.89
    蛱
    1.87
    婠
    1.83
     rése
    1.80
     normalt
    1.76
     inond
    1.75
     frança
    1.75
     écou
    1.71
     normaux
    1.70
    Activations Density 0.004%

    No Known Activations