© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1497
    Prev
    Next
    INDEX
    Explanations

    diverse linguistic contexts

    np_acts-logits-general · gemini-2.5-flash-lite

    punctuation delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ...
    0.30
    //
    0.26
    ​​​​
    0.24
    ❄
    0.24
    4
    0.24
    5
    0.23
    t
    0.23
    &&
    0.23
    >
    0.23
    sb
    0.23
    POSITIVE LOGITS
     acontecimientos
    0.24
     descripcion
    0.22
     frecuente
    0.21
     theorist
    0.21
    퇸
    0.21
     arrhythmia
    0.21
    رسٹ
    0.21
    ವೇಂದ್ರ
    0.21
     istek
    0.21
     ahuv
    0.21
    Activations Density 0.074%

    No Known Activations