© 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. 29824
    Prev
    Next
    INDEX
    Explanations

    powerful characters breaking things

    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
    autes
    0.42
    diag
    0.41
    alupe
    0.39
     hesitate
    0.39
     Structures
    0.38
    &$\
    0.38
    ඊ
    0.37
     stemming
    0.37
    Stem
    0.37
    Structures
    0.37
    POSITIVE LOGITS
     tastings
    0.45
    宰
    0.41
     tasting
    0.41
     молод
    0.38
     liquidated
    0.38
     Tasting
    0.38
     正規品
    0.38
     enfer
    0.38
     Liquid
    0.37
    Eid
    0.37
    Activations Density 0.004%

    No Known Activations