© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 190340
    Prev
    Next
    INDEX
    Explanations

    bloggers publish

    np_acts-logits-general · gemini-2.5-flash-lite

    greater than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mynd
    0.47
    ستان
    0.46
    ・
    0.45
     かわ
    0.45
     stakeholder
    0.44
     たい
    0.42
     mischiev
    0.42
     العزيز
    0.42
     entend
    0.42
    又は
    0.42
    POSITIVE LOGITS
     landfills
    0.45
    bbb
    0.44
    akk
    0.42
    ianthus
    0.41
    ουλ
    0.41
    끔
    0.40
    喽
    0.40
    ított
    0.40
    像素
    0.39
    हदी
    0.39
    Activations Density 0.001%

    No Known Activations