© 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. 11587
    Prev
    Next
    INDEX
    Explanations

    starts with is

    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
    StringUtils
    3.21
    ="<?=
    3.14
    шення
    3.04
    <bos>
    2.96
    লাইয়া
    2.95
    র্থ
    2.94
    RESSION
    2.91
    িশালী
    2.90
    顱
    2.90
    FirstResponder
    2.87
    POSITIVE LOGITS
    de
    2.87
    se
    2.73
    up
    2.59
    nd
    2.55
    te
    2.31
    kel
    2.26
    lands
    2.21
    簀
    2.19
    bas
    2.17
    rael
    2.16
    Activations Density 0.120%

    No Known Activations