© 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. 22-GEMMASCOPE-2-RES-16K
    7. 9299
    Prev
    Next
    INDEX
    Explanations

    ne followed by specific words

    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
    nics
    1.14
    rank
    1.13
    rances
    1.13
    Wrapped
    1.11
    r
    1.10
    rint
    1.07
     hùng
    1.06
    teurs
    1.06
    ومة
    1.04
    stay
    1.03
    POSITIVE LOGITS
    GLIGENCE
    1.09
    ighed
    1.08
    ؏
    1.08
    ѝ
    1.04
     に対
    1.01
    odymium
    1.01
    ი
    1.00
    талия
    0.99
    ៗ
    0.98
    哺乳
    0.98
    Activations Density 0.006%

    No Known Activations