© 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. 3301
    Prev
    Next
    INDEX
    Explanations

    time duration variables (n, t)

    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
    currentChar
    0.65
     ढाई
    0.62
    Ϣ
    0.62
     Charities
    0.61
    アナ
    0.60
    highlight
    0.60
     BVHTree
    0.60
     ও
    0.59
    highlights
    0.59
    chars
    0.58
    POSITIVE LOGITS
     months
    0.72
     years
    0.72
     weeks
    0.70
     time
    0.69
     seasons
    0.68
     trajet
    0.68
     tenure
    0.68
     pistons
    0.67
     pezzi
    0.66
     перио
    0.65
    Activations Density 0.002%

    No Known Activations