© 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. 66079
    Prev
    Next
    INDEX
    Explanations

    function and method calls

    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
     chcia
    -1.16
    面對
    -1.13
    幾乎
    -1.05
     sembler
    -1.03
     compró
    -1.03
     wysy
    -1.03
     powiedział
    -1.02
     zapy
    -1.02
     woda
    -1.00
     odpowiada
    -0.98
    POSITIVE LOGITS
     which
    1.39
     by
    1.16
     to
    0.95
     from
    0.94
    ibid
    0.94
     methods
    0.94
     pamamagitan
    0.93
    else
    0.91
    谙
    0.91
     irrespective
    0.90
    Activations Density 0.041%

    No Known Activations