© 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. 22-GEMMASCOPE-RES-131K
    7. 39160
    Prev
    Next
    INDEX
    Explanations

    positions and roles

    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
     farther
    -1.07
     świad
    -1.05
     ferner
    -1.02
     produce
    -0.96
    eronau
    -0.95
    LLAB
    -0.94
     produced
    -0.92
     beginning
    -0.92
     inmediatamente
    -0.91
    exels
    -0.91
    POSITIVE LOGITS
    oused
    1.01
    rably
    1.00
    $<$
    1.00
     calefacción
    0.98
     soms
    0.95
     petites
    0.94
     beserta
    0.93
     who
    0.93
    llllll
    0.90
     כוס
    0.90
    Activations Density 0.034%

    No Known Activations