© 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. 16192
    Prev
    Next
    INDEX
    Explanations

    UI lists, headings, and descriptions

    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
    焓
    0.42
    Beim
    0.42
     beim
    0.40
     Beim
    0.40
     एसएसपी
    0.39
     Hels
    0.39
    حر
    0.39
     Retirement
    0.37
     سایت
    0.37
    搧
    0.36
    POSITIVE LOGITS
     spinning
    0.41
     bubbly
    0.40
     baller
    0.40
     spines
    0.39
     dünyanın
    0.39
     sarcom
    0.39
     connective
    0.38
     spinner
    0.38
     Spinach
    0.38
    boxylate
    0.37
    Activations Density 0.000%

    No Known Activations