© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 4421
    Prev
    Next
    INDEX
    Explanations

    lying / curled / laying on

    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
    珐
    0.74
    ጥር
    0.73
     ഒഴിവാ
    0.72
     commutes
    0.71
     commute
    0.71
    祅
    0.71
    ટું
    0.70
    噌
    0.70
    专门
    0.69
     authorize
    0.69
    POSITIVE LOGITS
     lying
    1.57
     lifeless
    1.50
     unconscious
    1.50
     collapsed
    1.38
     lies
    1.35
     slumped
    1.31
     limp
    1.30
    躺
    1.25
     spraw
    1.24
     wounded
    1.18
    Activations Density 0.127%

    No Known Activations