© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95704
    Prev
    Next
    INDEX
    Explanations

    XML tag structures

    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
     насељу
    -1.06
    primaryStage
    -1.00
    Tämä
    -1.00
    hermes
    -0.96
    plakat
    -0.96
    gorro
    -0.94
    Freitag
    -0.93
     endforeach
    -0.93
    hdysval
    -0.92
     איך
    -0.91
    POSITIVE LOGITS
    losseum
    1.06
    each
    1.00
    —-
    1.00
     such
    1.00
     mesmas
    1.00
    k
    0.99
    a
    0.98
    his
    0.98
    e
    0.98
    h
    0.95
    Activations Density 0.000%

    No Known Activations