© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 332
    Prev
    Next
    INDEX
    Explanations

    actions and expressions

    np_acts-logits-general · gemini-2.5-flash-lite

    brushing against

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_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
     preponder
    0.55
     preponderance
    0.55
     judicious
    0.52
     precludes
    0.51
     wówczas
    0.50
     تسه
    0.48
    Notwithstanding
    0.48
     :-)
    0.47
     ;-)
    0.47
     substantive
    0.46
    POSITIVE LOGITS
     Taehyung
    0.81
     Jungkook
    0.77
     Jimin
    0.64
     chibi
    0.60
     annoyance
    0.59
     surprisingly
    0.58
     smirk
    0.58
     groaned
    0.58
     luckily
    0.56
     aswell
    0.56
    Activations Density 0.074%

    No Known Activations