© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74341
    Prev
    Next
    INDEX
    Explanations

    android attributes

    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
     vocale
    -1.69
     constater
    -1.63
    ;%%
    -1.59
     majest
    -1.57
    訁
    -1.56
    ㎎
    -1.55
    vollen
    -1.54
    endwhile
    -1.49
    TRIBUTES
    -1.48
    ##
    -1.45
    POSITIVE LOGITS
     it
    2.16
    .
    2.05
     other
    1.80
     each
    1.72
     there
    1.65
    よる
    1.63
     even
    1.59
     this
    1.55
     etc
    1.45
    )
    1.42
    Activations Density 0.144%

    No Known Activations