© 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. 3320
    Prev
    Next
    INDEX
    Explanations

    /* comments */

    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
     organismo
    0.51
     polyphen
    0.50
     gentamicin
    0.46
     क्लोरीन
    0.46
    +](=
    0.45
    খেজুর
    0.45
     pyrid
    0.45
    segaretro
    0.45
     dakkh
    0.45
    ىڭ
    0.45
    POSITIVE LOGITS
    re
    0.54
    un
    0.54
    use
    0.53
    x
    0.53
    ’
    0.53
    id
    0.52
    0
    0.52
    ru
    0.51
    <0x0D>
    0.51
    ros
    0.51
    Activations Density 0.002%

    No Known Activations