© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 3303
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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_all/layer_41_width_262k_l0_big
    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
     ذریع
    0.33
     മിക
    0.33
     এইরূপে
    0.33
    vvvert
    0.33
    ยายาม
    0.32
    <unused218>
    0.32
    assaytype
    0.31
    <unused303>
    0.31
    <unused289>
    0.31
    <unused328>
    0.31
    POSITIVE LOGITS
    1
    0.47
    0
    0.46
    2
    0.39
    5
    0.39
     to
    0.35
    3
    0.35
    d
    0.33
    in
    0.33
    ↵
    0.33
    l
    0.33
    Activations Density 0.058%

    No Known Activations