© 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. 12381
    Prev
    Next
    INDEX
    Explanations

    programming languages diversity

    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
    providedIn
    -1.34
    мм
    -1.16
     lace
    -1.16
     culturelle
    -1.12
     pirm
    -1.09
    ))}
    -1.08
    психо
    -1.06
    еру
    -1.04
     søndag
    -1.03
    ༵
    -1.02
    POSITIVE LOGITS
     când
    1.16
     două
    1.11
     diversos
    1.02
    ↵↵
    1.02
     вона
    1.00
     größe
    0.99
     nenhuma
    0.99
    raszam
    0.98
     ENTIRE
    0.97
    пления
    0.97
    Activations Density 0.002%

    No Known Activations