© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 4974
    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-2-4b-it/resid_post/layer_29_width_65k_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
     terse
    0.72
    Git
    0.68
     Bolsonaro
    0.68
     sigh
    0.67
    обс
    0.66
     सविता
    0.66
     রাক
    0.66
    卍
    0.65
     smoothie
    0.64
     Animation
    0.64
    POSITIVE LOGITS
     ear
    3.45
     ears
    3.13
     Ear
    3.11
    Ear
    3.04
    耳
    2.85
     hearing
    2.68
     Ears
    2.67
    耳朵
    2.65
     耳
    2.59
     Hearing
    2.53
    Activations Density 0.113%

    No Known Activations