© 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. 82263
    Prev
    Next
    INDEX
    Explanations

    4 followed by channels 10G

    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
     κά
    0.53
    ش
    0.48
     crawls
    0.48
    衅
    0.47
     शत
    0.46
    دود
    0.46
    蛔
    0.45
     Drainage
    0.44
     belie
    0.44
    夼
    0.44
    POSITIVE LOGITS
    uvad
    0.53
    ومی
    0.48
    লাষ
    0.47
    mba
    0.46
    туга
    0.46
    keun
    0.46
    に使
    0.44
    renzia
    0.43
    oneg
    0.43
    hatti
    0.42
    Activations Density 0.000%

    No Known Activations