© 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. 13-GEMMASCOPE-2-RES-16K
    7. 10808
    Prev
    Next
    INDEX
    Explanations

    units of measurement, information, and quantity

    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
     திட்டம்
    1.18
     rapporto
    1.14
    ี่ยม
    1.09
     voll
    1.08
    𝘰
    1.05
    잔
    1.04
     sij
    1.04
    ציה
    1.03
    ́i
    1.02
     carrera
    1.02
    POSITIVE LOGITS
     publishing
    1.14
     редак
    1.13
     文
    1.13
     whereby
    1.09
    fmt
    1.09
    thern
    1.09
     eaten
    1.08
    dust
    1.07
    呈現
    1.07
     которой
    1.07
    Activations Density 0.000%

    No Known Activations