© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 10556
    Prev
    Next
    INDEX
    Explanations

    "Holi crap" and mixed languages

    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
    ঃখ
    2.05
    substack
    2.04
    weets
    2.04
    ="{{
    2.02
    upper
    2.00
     NSFW
    1.95
    pim
    1.94
    ς
    1.91
    ville
    1.88
    wine
    1.85
    POSITIVE LOGITS
    ка
    2.29
     मन
    2.21
    ник
    2.16
    Би
    2.13
    дер
    2.10
    توان
    2.07
    inį
    2.07
     اطلا
    2.06
    довж
    2.03
    ংকার
    1.98
    Activations Density 0.033%

    No Known Activations