© 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. 13479
    Prev
    Next
    INDEX
    Explanations

    Draft Dodger

    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
     Turns
    1.33
     Strang
    1.32
    seits
    1.30
     famously
    1.28
     Kampf
    1.28
    ,":
    1.27
    .,"
    1.26
    ǃ
    1.25
     Кстати
    1.25
     wildly
    1.25
    POSITIVE LOGITS
     poter
    1.32
     she
    1.31
    렜
    1.25
     delen
    1.23
     adelant
    1.18
     दिलों
    1.18
     необхідно
    1.17
    radas
    1.17
    ന്നും
    1.15
     he
    1.15
    Activations Density 0.067%

    No Known Activations