© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12176
    Prev
    Next
    INDEX
    Explanations

    words following "the" or "/*"

    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
     熊
    -1.16
    
    -1.09
    jelaskan
    -1.05
    🈵
    -1.05
     Dí
    -1.00
    '][]
    -0.97
     Grá
    -0.96
     againſt
    -0.95
    Ethylbenzene
    -0.95
    UEGO
    -0.95
    POSITIVE LOGITS
    s
    1.14
     hielt
    1.00
     trois
    0.99
    鰹
    0.98
     effect
    0.96
     nowy
    0.95
    Tratamiento
    0.94
     следующее
    0.94
     нынеш
    0.91
     య
    0.91
    Activations Density 0.000%

    No Known Activations