© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11647
    Prev
    Next
    INDEX
    Explanations

    ggplot aes function calls

    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
     ا
    1.97
     با
    1.76
     «
    1.70
     ار
    1.63
     ام
    1.62
    딘
    1.61
     مثلث
    1.59
     C
    1.58
     الت
    1.56
     ر
    1.56
    POSITIVE LOGITS
    ঁজ
    1.92
    য়োগ
    1.65
    servicetime
    1.65
     veniam
    1.61
    idxs
    1.61
    াকাল
    1.61
    isComposite
    1.58
     unapolog
    1.54
     interstitials
    1.54
    ysm
    1.53
    Activations Density 0.024%

    No Known Activations