© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11396
    Prev
    Next
    INDEX
    Explanations

    would just be

    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
    цької
    0.45
     diversa
    0.44
    يرات
    0.44
    нік
    0.43
     frem
    0.43
    .+
    0.43
     CHAMP
    0.42
     tuv
    0.42
     אוי
    0.42
    敵
    0.42
    POSITIVE LOGITS
    JSON
    0.43
    赌场
    0.42
    json
    0.41
     bankruptcy
    0.41
     repro
    0.40
    ത്തിനു
    0.40
     JSON
    0.40
    开源
    0.40
    amburger
    0.39
    Csv
    0.39
    Activations Density 0.001%

    No Known Activations