© 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. 217288
    Prev
    Next
    INDEX
    Explanations

    trash made, bait tackle, garage door

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

    list item separators

    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
    xis
    0.45
    inelli
    0.44
     expliqué
    0.44
     ヤ
    0.43
    ributedString
    0.43
    espresso
    0.42
     cataly
    0.42
     Націона
    0.42
     Giuseppe
    0.41
    iders
    0.40
    POSITIVE LOGITS
    ৭১
    0.49
    ेड
    0.47
     Americans
    0.46
     Bereichen
    0.45
     çift
    0.45
    ዙ
    0.44
     ć
    0.43
     большинства
    0.43
     cwd
    0.43
    ่อย
    0.43
    Activations Density 0.000%

    No Known Activations