© 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. 8759
    Prev
    Next
    INDEX
    Explanations

    identification or specification

    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
    un
    0.49
     producing
    0.49
    p
    0.48
    w
    0.48
     excepted
    0.46
     in
    0.45
     sexuality
    0.44
    r
    0.44
    rVert
    0.43
    ugno
    0.42
    POSITIVE LOGITS
    漫畫
    0.52
    컹
    0.52
     μέρος
    0.52
    胖
    0.51
    ›
    0.50
     záb
    0.48
    ğini
    0.48
     malzeme
    0.47
    擀
    0.47
    互動
    0.47
    Activations Density 0.000%

    No Known Activations