© 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. 81858
    Prev
    Next
    INDEX
    Explanations

    business, account, withdraw, sellers, claims

    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
     ST
    0.46
     sneak
    0.45
    emphas
    0.45
     SO
    0.45
     CHARSET
    0.43
     X
    0.42
     custom
    0.42
     negate
    0.42
     strict
    0.41
     insistent
    0.41
    POSITIVE LOGITS
    馚
    0.48
    煐
    0.48
    ม
    0.47
     ฟรี
    0.45
    ’
    0.45
    Trung
    0.45
    嬋
    0.45
     reflexión
    0.44
    ---’
    0.44
    लोकन
    0.44
    Activations Density 0.006%

    No Known Activations