© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12392
    Prev
    Next
    INDEX
    Explanations

    comments explaining parameters

    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
     부분을
    1.51
    բ
    1.50
     單
    1.45
     라는
    1.44
     ஏனெ
    1.43
     것도
    1.42
     ავ
    1.41
     Verkehr
    1.40
    ﺬ
    1.39
     그러
    1.39
    POSITIVE LOGITS
    นาย
    1.55
     gestione
    1.42
     grassroots
    1.41
    uela
    1.40
    istas
    1.39
    Allen
    1.39
     llevan
    1.39
    preet
    1.38
    UEL
    1.37
    Jackie
    1.37
    Activations Density 0.032%

    No Known Activations