© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 5182
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_262k_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
    /
    0.95
     your
    0.95
     you
    0.92
     uses
    0.89
     goes
    0.82
     relates
    0.81
     [
    0.78
     a
    0.78
     (
    0.78
     creates
    0.78
    POSITIVE LOGITS
     aveva
    1.17
     había
    1.13
     hắn
    1.02
     είχε
    1.02
     habían
    0.99
     avevano
    0.99
     avrebbe
    0.95
     havia
    0.95
     ήταν
    0.93
     знал
    0.92
    Activations Density 0.020%

    No Known Activations