© 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. 199903
    Prev
    Next
    INDEX
    Explanations

    removing redundancy or comparing options

    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
    提名
    0.48
     WHICH
    0.45
     Шрифт
    0.44
     !}\
    0.44
    關於
    0.43
    說是
    0.43
    avoro
    0.43
    ༅
    0.43
     Saúde
    0.43
     Sociology
    0.42
    POSITIVE LOGITS
    Flex
    0.46
     yourself
    0.46
     faster
    0.45
    +
    0.45
     effortless
    0.44
     extras
    0.43
     или
    0.43
     uppercase
    0.42
     temporarily
    0.41
    来自
    0.41
    Activations Density 0.002%

    No Known Activations