© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82836
    Prev
    Next
    INDEX
    Explanations

    ear and hearing

    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
    ஐ
    0.41
    悎
    0.39
     Viol
    0.38
     äh
    0.38
     পড়িল
    0.38
     GRID
    0.37
     UX
    0.37
    न्नई
    0.37
    読む
    0.37
    ði
    0.36
    POSITIVE LOGITS
     ear
    1.01
     tinnitus
    0.97
     hearing
    0.91
     Ear
    0.87
     Hearing
    0.86
    귓
    0.86
    耳
    0.84
    Ear
    0.84
    👂
    0.83
     audi
    0.82
    Activations Density 0.047%

    No Known Activations