© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 12963
    Prev
    Next
    INDEX
    Explanations

    glasses

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Resolver
    0.57
    онер
    0.51
    醒
    0.51
    に応
    0.49
     dauer
    0.49
     decreases
    0.49
     resc
    0.49
    胿
    0.49
     resolution
    0.49
     متع
    0.48
    POSITIVE LOGITS
    👽
    0.68
    )}]{
    0.66
    Mgr
    0.64
    🙈
    0.63
    glasses
    0.59
     glasses
    0.58
    거든요
    0.58
    Lyric
    0.57
    भावना
    0.57
    Lik
    0.56
    Activations Density 0.000%

    No Known Activations