© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 15806
    Prev
    Next
    INDEX
    Explanations

    git commands

    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
     다운
    2.33
    Ỹ
    2.31
    ەکە
    2.20
    uden
    2.18
    ಶ್ಚ
    2.17
    Луч
    2.15
    ‍ह
    2.14
    ήμε
    2.14
    Ud
    2.13
    living
    2.13
    POSITIVE LOGITS
    ჭ
    2.39
    zag
    2.11
    🏻
    2.10
    gets
    2.09
    rola
    2.03
    oncé
    2.02
    rol
    1.97
     override
    1.96
     Expect
    1.95
    .°
    1.95
    Activations Density 0.110%

    No Known Activations