© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8346
    Prev
    Next
    INDEX
    Explanations

    web URLs

    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_22_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
    juk
    0.92
    मोन
    0.92
    폼
    0.88
    jom
    0.87
    action
    0.84
     Monate
    0.83
    gon
    0.83
    CURSOR
    0.82
    ylist
    0.81
    nast
    0.81
    POSITIVE LOGITS
    分享
    1.25
     सम्मिल
    1.12
     compartilh
    1.10
    榻
    1.10
     cared
    1.07
     actuated
    1.04
    enaire
    1.03
    壑
    0.99
     diabetics
    0.98
    Sponsored
    0.97
    Activations Density 0.000%

    No Known Activations