© 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. 3621
    Prev
    Next
    INDEX
    Explanations

    bowling ball analogy

    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
    ء
    2.26
    करों
    2.09
    vue
    2.00
    financial
    1.99
    falling
    1.94
    autore
    1.91
    न्द्र
    1.85
    ffect
    1.85
    न्द्रीय
    1.84
    groom
    1.83
    POSITIVE LOGITS
    য়ের
    2.63
    s
    2.52
    ˏ
    2.48
    น์
    2.41
    য়ের
    2.41
    elage
    2.36
    sman
    2.33
     Reign
    2.32
    ⼀
    2.28
    ات
    2.27
    Activations Density 0.006%

    No Known Activations