© 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. 15727
    Prev
    Next
    INDEX
    Explanations

    angular, scope, app

    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
     a
    -1.21
    是
    -1.15
    #%%
    -1.09
     sitzt
    -1.05
     Pakistan
    -1.02
     самый
    -1.02
     Etik
    -1.02
     UK
    -1.02
    queryParams
    -1.00
     juta
    -0.98
    POSITIVE LOGITS
     OREGON
    1.17
     necesarios
    1.13
    zzá
    1.08
    竅
    1.06
    irinha
    1.05
     xing
    1.03
     SPARK
    1.02
    rescu
    0.99
     hansen
    0.98
     wrapping
    0.97
    Activations Density 0.058%

    No Known Activations