© 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. 53-GEMMASCOPE-2-RES-262K
    7. 40023
    Prev
    Next
    INDEX
    Explanations

    mouth and mouth-related terms

    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_53_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
    珵
    0.41
    atsiya
    0.37
    媺
    0.37
    蠵
    0.37
     Soll
    0.37
    紾
    0.36
    傃
    0.35
    Š
    0.35
    צב
    0.35
    䇝
    0.35
    POSITIVE LOGITS
     mouth
    4.03
     Mouth
    3.63
    mouth
    3.44
     mouths
    3.42
     mulut
    3.00
    口
    2.95
     miệng
    2.53
    嘴
    2.52
     bouche
    2.47
     boca
    2.42
    Activations Density 0.031%

    No Known Activations