© 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-65K
    7. 330
    Prev
    Next
    INDEX
    Explanations

    section numbering like 2. or 3

    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_65k_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
    ри
    0.64
    ra
    0.52
     (
    0.52
    ла
    0.52
    ;
    0.47
    ти
    0.46
    .
    0.46
    ،
    0.41
    。
    0.40
     tradition
    0.39
    POSITIVE LOGITS
     órg
    0.54
    P
    0.53
    ສາມາດ
    0.52
    ມັນ
    0.52
     ﺍﻟ
    0.52
     to
    0.50
     aumento
    0.50
    ව
    0.49
    માં
    0.49
     asker
    0.49
    Activations Density 0.402%

    No Known Activations