© 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. 34-GEMMASCOPE-RES-131K
    7. 109791
    Prev
    Next
    INDEX
    Explanations

    numbers, symbols, and foreign words

    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_34/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
    zustand
    -0.83
     anche
    -0.81
    LLL
    -0.81
    Еще
    -0.81
     Mug
    -0.80
    ledad
    -0.80
     ठ
    -0.79
    ḿ
    -0.79
    urlencoded
    -0.78
    verstanden
    -0.78
    POSITIVE LOGITS
    到着
    0.89
     perfetta
    0.89
     meravigli
    0.84
     attiva
    0.83
     reconoce
    0.82
    ərb
    0.81
     повідом
    0.80
     ejecutar
    0.78
     reemplazar
    0.78
    penta
    0.77
    Activations Density 0.007%

    No Known Activations