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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11416
    Prev
    Next
    INDEX
    Explanations

    selection of grid coordinates or interface elements

    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
    figurine
    -1.05
    jaket
    -1.03
     also
    -1.03
    yyj
    -1.01
     Wappen
    -0.99
    gorro
    -0.98
     agresión
    -0.96
    gilet
    -0.96
     here
    -0.94
    turkish
    -0.92
    POSITIVE LOGITS
    iostream
    1.01
     milliard
    1.01
     FRAG
    0.98
     risiko
    0.96
    ̣t
    0.95
     geograf
    0.95
     kamb
    0.94
    hrte
    0.93
    better
    0.93
     повсе
    0.92
    Activations Density 0.002%

    No Known Activations