© 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. 15596
    Prev
    Next
    INDEX
    Explanations

    shell scripting 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
    身影
    0.44
    
    0.38
    峠
    0.38
    记得
    0.37
    チーズ
    0.37
    ሴ
    0.37
    ューズ
    0.36
    ធ្វើ
    0.35
    entionally
    0.35
    ಳಿಗೆ
    0.35
    POSITIVE LOGITS
     shell
    1.19
     Shell
    1.19
    Shell
    1.16
     shells
    1.02
    shell
    0.93
     shelling
    0.91
    🐚
    0.87
     shellfish
    0.86
    殼
    0.82
     shelled
    0.82
    Activations Density 0.008%

    No Known Activations