© 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. 59560
    Prev
    Next
    INDEX
    Explanations

    instrumented or Pranic

    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
    ”
    -2.83
     he
    -2.80
    轳
    -2.75
    ᯾
    -2.55
    CHREIB
    -2.45
    맏
    -2.41
    糨
    -2.39
    .’”
    -2.39
    
    -2.36
    </u>
    -2.33
    POSITIVE LOGITS
    o
    2.77
     If
    2.75
    h
    2.63
    ⦊
    2.58
    ться
    2.38
    𐑂
    2.33
    讴
    2.27
     He
    2.14
     marshes
    2.08
     RSITY
    2.08
    Activations Density 0.009%

    No Known Activations