© 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. 22-GEMMASCOPE-2-RES-65K
    7. 5726
    Prev
    Next
    INDEX
    Explanations

    ears and headphones

    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_22_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
     ราช
    0.75
     सविता
    0.68
     Tudor
    0.68
     Animated
    0.67
    팩
    0.65
    Animations
    0.64
     ரொ
    0.63
     उमेश
    0.63
    फ़ी
    0.63
     NoSuch
    0.63
    POSITIVE LOGITS
     headphones
    2.71
     ear
    2.69
     ears
    2.54
     earbuds
    2.48
     earphones
    2.47
    👂
    2.40
     headphone
    2.38
     hearing
    2.36
     Hearing
    2.35
     Ear
    2.34
    Activations Density 0.168%

    No Known Activations