© 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. 16-GEMMASCOPE-2-RES-262K
    7. 19838
    Prev
    Next
    INDEX
    Explanations

    return type declarations

    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_16_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
    ﻮ
    0.74
    რება
    0.73
    وله
    0.66
    ა
    0.65
    ד
    0.65
    टान
    0.64
    રા
    0.64
    ரை
    0.63
    ből
    0.63
    ानी
    0.62
    POSITIVE LOGITS
    도
    0.93
     помощь
    0.83
    ও
    0.83
     be
    0.82
    も
    0.81
    在
    0.78
     σε
    0.74
     cần
    0.73
     getir
    0.72
     interesse
    0.72
    Activations Density 0.003%

    No Known Activations