© 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. 99330
    Prev
    Next
    INDEX
    Explanations

    python library imports

    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
     actriz
    -1.55
    bbero
    -1.53
     JUDICIAL
    -1.52
     ENVIRONMENTAL
    -1.52
     depois
    -1.50
     celu
    -1.50
     BASIN
    -1.49
     seulement
    -1.49
     EXPEND
    -1.49
    ᒍ
    -1.48
    POSITIVE LOGITS
     It
    2.03
     Hence
    1.81
    :
    1.80
    0
    1.72
    It
    1.66
     ſmall
    1.66
     WANT
    1.61
    ,
    1.60
     Thus
    1.59
     Seventy
    1.48
    Activations Density 0.006%

    No Known Activations