© 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. 11558
    Prev
    Next
    INDEX
    Explanations

    code syntax, punctuation, and symbols

    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
     (
    -1.29
     corrientes
    -1.21
     the
    -1.10
     sorry
    -1.05
     prawie
    -1.02
    pektrum
    -1.02
     esencial
    -0.99
    ଃ
    -0.98
    ྄
    -0.98
     herramientas
    -0.96
    POSITIVE LOGITS
    RESUMEN
    1.17
    ♪♪
    1.16
    ★★★
    1.11
    ariConfig
    1.09
    商品説明
    1.07
    izoen
    1.05
     appartamento
    1.05
     ͡°
    1.05
    ※※
    1.04
    Medal
    1.02
    Activations Density 0.030%

    No Known Activations