© 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. 11235
    Prev
    Next
    INDEX
    Explanations

    library names

    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
    jecture
    2.48
    ㄸ
    2.41
    ש
    2.39
    Jeh
    2.37
    boundingBox
    2.36
    ᾽
    2.33
    문제
    2.29
    嘆
    2.29
     Ehnergii
    2.28
     putt
    2.27
    POSITIVE LOGITS
    ক
    2.01
    bě
    1.86
    assara
    1.79
     możli
    1.79
    uluh
    1.70
     anlaş
    1.69
    ôtels
    1.69
    uden
    1.68
    يران
    1.68
    orten
    1.67
    Activations Density 0.036%

    No Known Activations