© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 16817
    Prev
    Next
    INDEX
    Explanations

    process automation, language models

    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
    :
    0.63
    ė
    0.51
    8
    0.48
     .
    0.45
    mai
    0.42
    .
    0.41
    and
    0.41
     !=
    0.40
    it
    0.39
     >=
    0.39
    POSITIVE LOGITS
    鸪
    0.44
    OpportunitiesBy
    0.43
     这些
    0.42
     ചില
    0.41
    lyPlugin
    0.41
     горо
    0.41
    艋
    0.41
     రో
    0.39
    tBleStatus
    0.38
    膯
    0.38
    Activations Density 0.118%

    No Known Activations