© 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. 4107
    Prev
    Next
    INDEX
    Explanations

    degree of qualities

    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
    storey
    1.14
     fucking
    1.13
    ّ
    1.10
     damned
    1.08
    ର
    1.07
    כן
    1.05
     ridiculously
    1.02
    G
    1.00
     (!)
    0.99
     damn
    0.99
    POSITIVE LOGITS
    。【
    1.31
    。<
    1.18
    íu
    1.14
     llevará
    1.11
    换
    1.05
    㗽
    1.02
    崬
    1.01
    uene
    1.00
    unud
    1.00
    uncul
    1.00
    Activations Density 0.512%

    No Known Activations