© 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. 168683
    Prev
    Next
    INDEX
    Explanations

    speech and special characters

    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
     fieldwork
    0.48
    </li>
    0.47
     (~
    0.46
     Retrieved
    0.42
    rums
    0.40
     Taiwanese
    0.40
     Kowloon
    0.40
     (
    0.40
    직
    0.40
    </td>
    0.40
    POSITIVE LOGITS
    릭터
    0.50
     Василий
    0.48
     அம்
    0.47
    м
    0.46
    나
    0.45
    니다
    0.44
    ərd
    0.44
     않습니다
    0.43
     nós
    0.43
    大的
    0.43
    Activations Density 0.001%

    No Known Activations