© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 57444
    Prev
    Next
    INDEX
    Explanations

    specific elements

    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
    一
    0.53
    ু
    0.50
    轼
    0.48
    警察
    0.47
     skup
    0.46
    初心
    0.46
    িন
    0.46
    那些
    0.46
    פק
    0.46
    ת
    0.46
    POSITIVE LOGITS
    atta
    0.57
    ables
    0.50
    </h1>
    0.50
    ären
    0.49
    opard
    0.49
    ideo
    0.48
    ata
    0.47
    ovir
    0.46
    abilité
    0.46
    ijo
    0.45
    Activations Density 0.000%

    No Known Activations