© 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. 40-GEMMASCOPE-2-RES-262K
    7. 84314
    Prev
    Next
    INDEX
    Explanations

    Non-disclosure agreements and code

    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_40_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
    ↵
    0.26
    a
    0.24
    s
    0.24
    ↵↵
    0.23
     a
    0.23
    -
    0.23
     (
    0.22
    U
    0.22
    ,
    0.22
    S
    0.22
    POSITIVE LOGITS
     मायणी
    0.21
    んにちは
    0.19
     কথোপ
    0.19
     Calyce
    0.19
     ஆர்ட்டெமி
    0.19
    Prothorax
    0.19
     বিটিআই
    0.19
    پيديا
    0.18
    මුත්
    0.18
     BlueprintName
    0.18
    Activations Density 0.000%

    No Known Activations