© 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. 13-GEMMASCOPE-2-RES-16K
    7. 11126
    Prev
    Next
    INDEX
    Explanations

    over followed by another word

    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
    elecimento
    2.86
     Crystallogr
    2.71
    ʣ
    2.65
    woorden
    2.59
    व्र
    2.55
    要
    2.55
    ård
    2.53
    éraux
    2.52
    ौड़
    2.48
     Cio
    2.45
    POSITIVE LOGITS
    不及
    2.65
    ्र
    2.61
     hinaus
    2.53
    hmann
    2.44
    сть
    2.34
    whelming
    2.30
    holt
    2.24
    pf
    2.18
    ্ক
    2.15
    뷰
    2.14
    Activations Density 0.328%

    No Known Activations