© 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. 72061
    Prev
    Next
    INDEX
    Explanations

    list delimiters

    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
     both
    -1.43
     two
    -1.30
     should
    -1.14
     with
    -1.13
     दोनों
    -1.07
     did
    -1.06
     Both
    -1.05
    Both
    -1.05
     would
    -1.04
     Almost
    -1.02
    POSITIVE LOGITS
     others
    1.12
     continuer
    1.09
     fuis
    1.05
     остальные
    1.03
     dégust
    1.02
     colonie
    1.01
     commencer
    1.01
     quitt
    1.00
    其余
    0.99
     دیگران
    0.99
    Activations Density 0.044%

    No Known Activations