© 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. 109725
    Prev
    Next
    INDEX
    Explanations

    hexadecimal codes and numbers

    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
     fiercely
    0.38
    uous
    0.36
    pathetic
    0.34
    𒉿
    0.34
     ঝড়
    0.33
     Fawcett
    0.33
     Lorentz
    0.32
    derick
    0.32
     ჩატი
    0.32
    ↵
    0.32
    POSITIVE LOGITS
     и
    0.40
    0.39
     και
    0.38
     их
    0.38
     it
    0.36
    ле
    0.34
     mío
    0.34
     exceed
    0.32
    $\
    0.31
     và
    0.31
    Activations Density 0.055%

    No Known Activations