© 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. 195692
    Prev
    Next
    INDEX
    Explanations

    introducing comparisons or firsts

    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
     ла
    0.51
     &'
    0.42
    utas
    0.39
     &-
    0.38
     -&
    0.38
     RS
    0.38
    荣誉
    0.38
     ஏ
    0.37
    explained
    0.37
    FREE
    0.37
    POSITIVE LOGITS
     steepest
    0.39
    采样
    0.37
    یدار
    0.36
    sections
    0.35
    ولز
    0.35
     steeper
    0.35
    ራዊ
    0.34
     worldRank
    0.34
    Sprite
    0.34
     portada
    0.34
    Activations Density 0.000%

    No Known Activations