© 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. 31-GEMMASCOPE-2-RES-262K
    7. 143515
    Prev
    Next
    INDEX
    Explanations

    where to find specific 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_31_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
     jakie
    0.46
    Computer
    0.45
     gift
    0.42
    Wat
    0.41
    Meh
    0.41
    锺
    0.40
    Calculator
    0.40
    Atm
    0.40
    Gall
    0.40
    计量
    0.40
    POSITIVE LOGITS
    ar
    0.51
    '",
    0.48
     партия
    0.48
     famílias
    0.48
    thapi
    0.48
     esclav
    0.48
     attenuate
    0.48
     partido
    0.47
    "},
    0.47
     Conselho
    0.45
    Activations Density 0.006%

    No Known Activations