© 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. 688
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    abbanti
    0.33
    acariy
    0.33
    ড্রিম
    0.31
    trashItem
    0.30
    rvGroup
    0.30
    itabbo
    0.30
    ---’
    0.29
    <unused77>
    0.29
    assaytype
    0.29
    akkhati
    0.28
    POSITIVE LOGITS
    0.45
    4
    0.38
    1
    0.37
    0
    0.37
    5
    0.37
    6
    0.35
    -
    0.33
    8
    0.33
     $
    0.32
     D
    0.32
    Activations Density 0.248%

    No Known Activations