© 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. 90328
    Prev
    Next
    INDEX
    Explanations

    foreign language components

    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
    मु
    0.47
    ιον
    0.45
    αυ
    0.44
     sickness
    0.43
     பகை
    0.43
    َق
    0.43
     conflictos
    0.43
     irrepar
    0.42
    Ꮩ
    0.42
     chơi
    0.41
    POSITIVE LOGITS
    เพื่อให้
    0.44
    0.41
     Akh
    0.40
     לס
    0.40
     Water
    0.40
     Wang
    0.40
    Generated
    0.40
    Fallback
    0.39
    elevationMap
    0.39
     hydrolysis
    0.39
    Activations Density 0.006%

    No Known Activations