© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3314
    Prev
    Next
    INDEX
    Explanations

    duration or how long it lasts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
         
    0.52
    0
    0.50
    -
    0.47
    ",
    0.46
    ")
    0.45
    **
    0.43
    દેશ
    0.43
    ";
    0.43
     ইঙ্গ
    0.42
    categorical
    0.42
    POSITIVE LOGITS
     duration
    1.03
     durata
    0.99
     durée
    0.97
     дли
    0.95
     durations
    0.93
     lasts
    0.90
     lasting
    0.90
    duration
    0.89
     lasted
    0.84
     longer
    0.83
    Activations Density 0.035%

    No Known Activations