© 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. 31939
    Prev
    Next
    INDEX
    Explanations

    styled-components CSS in JS

    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
     reforma
    0.59
     sajana
    0.59
    꾿
    0.58
    новой
    0.57
    стым
    0.57
     rupam
    0.57
    ліся
    0.57
     antigos
    0.57
    Ⲕ
    0.57
    лянчук
    0.57
    POSITIVE LOGITS
    `
    0.77
     մ
    0.56
    ր
    0.56
     պ
    0.54
    `(
    0.50
    տ
    0.49
    ում
    0.48
    աց
    0.48
    ե
    0.48
    ել
    0.47
    Activations Density 0.001%

    No Known Activations