© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13499
    Prev
    Next
    INDEX
    Explanations

    say "interval"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_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
    पीठ
    0.58
     Duc
    0.54
    絲
    0.49
    ographies
    0.49
     Stere
    0.49
    seiten
    0.49
    üsse
    0.49
    麩
    0.48
    লাষ
    0.48
     شخصیت
    0.48
    POSITIVE LOGITS
     interval
    4.78
     intervals
    4.59
    interval
    4.59
     Interval
    4.56
    Interval
    4.44
     INTERVAL
    4.28
    intervals
    4.25
     Intervals
    4.22
    INTERVAL
    4.09
     intervalo
    3.95
    Activations Density 0.036%

    No Known Activations