© 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. 22-GEMMASCOPE-RES-131K
    7. 34388
    Prev
    Next
    INDEX
    Explanations

    separate from

    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_22/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
     čast
    -0.96
    paar
    -0.95
    gx
    -0.94
     realistas
    -0.93
    旆
    -0.93
     değişik
    -0.92
    estría
    -0.92
     ilgili
    -0.91
    Geografie
    -0.90
    此人
    -0.90
    POSITIVE LOGITS
     from
    1.59
     separating
    1.34
     separates
    1.23
     Separation
    1.18
     Separate
    1.13
    separated
    1.12
    Separation
    1.11
     separated
    1.09
    separate
    1.03
     Separator
    1.03
    Activations Density 0.089%

    No Known Activations