© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13810
    Prev
    Next
    INDEX
    Explanations

    specific situations or behaviors

    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_13_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
     رئيس
    1.36
     Proficiency
    1.35
    शिता
    1.32
    <unused1966>
    1.31
     നമഃ
    1.31
    嵇
    1.30
     구매
    1.29
     கெல்வின்
    1.29
    कृतिक
    1.28
    Ʌ
    1.27
    POSITIVE LOGITS
    2
    0.91
    1
    0.86
    oin
    0.83
     delt
    0.81
     zau
    0.80
     draw
    0.80
    5
    0.79
     doves
    0.77
     viewed
    0.77
    xi
    0.77
    Activations Density 0.000%

    No Known Activations