© 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. 17979
    Prev
    Next
    INDEX
    Explanations

    new members

    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
     impactful
    0.73
     ChatGPT
    0.71
    めっちゃ
    0.70
    🥲
    0.70
     проє
    0.70
     microbiome
    0.68
    🥹
    0.68
     ✨
    0.67
     iteratively
    0.67
     проєкту
    0.66
    POSITIVE LOGITS
    
    0.66
     সত্যিকার
    0.64
     coloro
    0.61
     dependability
    0.60
    可以让
    0.59
    或者是
    0.56
     quelquefois
    0.55
    的时候
    0.55
     כאשר
    0.55
    这个时候
    0.54
    Activations Density 0.000%

    No Known Activations