© 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. 11358
    Prev
    Next
    INDEX
    Explanations

    data and code structure

    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
     exceptionally
    -1.16
    Život
    -1.13
    一直
    -1.11
     trám
    -1.10
     parfois
    -1.08
     schützen
    -1.04
     prípade
    -1.04
     REALLY
    -1.04
     relentless
    -1.03
     первых
    -1.03
    POSITIVE LOGITS
     parque
    1.12
    ಝ
    1.10
     by
    1.10
    1.09
     before
    1.08
     more
    1.06
    曲を
    1.03
    1.02
     musique
    1.02
     while
    1.02
    Activations Density 0.001%

    No Known Activations