© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10982
    Prev
    Next
    INDEX
    Explanations

    time periods of a decade

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    ことが
    2.97
    sup
    2.94
    tete
    2.90
    tt
    2.88
    tub
    2.82
    sit
    2.77
    t
    2.74
    tte
    2.71
     "@{
    2.69
    tze
    2.69
    POSITIVE LOGITS
    𝑟
    2.81
    an
    2.65
    وید
    2.59
    𝓇
    2.52
    Keb
    2.51
    ﻓ
    2.47
    啪
    2.47
    ऊन
    2.47
    𝑢
    2.44
    ೂ
    2.41
    Activations Density 0.037%

    No Known Activations