© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 66120
    Prev
    Next
    INDEX
    Explanations

    time, future, or past events

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

    imagine, social, woman, she

    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_31_width_262k_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
     cumpr
    0.47
     na
    0.46
     confl
    0.46
     leash
    0.46
     correto
    0.46
    .
    0.46
     catast
    0.45
     McLaughlin
    0.44
    วัส
    0.44
     pli
    0.43
    POSITIVE LOGITS
     акы
    0.51
     头
    0.46
     आठ
    0.46
     तीन
    0.45
    बिनेट
    0.45
    ᱞ
    0.45
     उच्च
    0.44
     свето
    0.44
     రాజ్య
    0.44
     জগৎ
    0.44
    Activations Density 0.002%

    No Known Activations