© 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-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 1500
    Prev
    Next
    INDEX
    Explanations

    importing pandas as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Antaeotricha
    0.43
    RELATIVA
    0.42
    蹬
    0.40
    ᔨ
    0.40
    ‍ह
    0.39
    ორციელ
    0.39
    <unused193>
    0.39
     बैक्टीरिया
    0.38
    ᔪ
    0.38
    <unused332>
    0.38
    POSITIVE LOGITS
    .*;
    0.72
    utils
    0.67
    _
    0.66
     import
    0.66
    ._
    0.60
    .*
    0.60
    util
    0.59
     utils
    0.57
    py
    0.55
    ::{
    0.55
    Activations Density 0.113%

    No Known Activations