© 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. 9
    Prev
    Next
    INDEX
    Explanations

    qualities and conditions

    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
     Mastery
    0.41
    ከናወ
    0.41
    lasti
    0.36
    ewöhn
    0.36
    ৃত
    0.36
    杨
    0.34
    imony
    0.34
    ogany
    0.34
    র্জাতিক
    0.34
     indented
    0.34
    POSITIVE LOGITS
     quotient
    0.49
     व
    0.44
     வாய்
    0.43
    十足
    0.43
     Quotient
    0.42
     ও
    0.42
     ו
    0.41
    盎
    0.40
    នៃការ
    0.40
    및
    0.40
    Activations Density 0.109%

    No Known Activations