© 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. 3504
    Prev
    Next
    INDEX
    Explanations

    anyone starting or interested

    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
    𝑒
    4.08
    ि
    3.62
    𝑖
    3.54
    𝑜
    3.53
    i
    3.46
    ar
    3.40
    い
    3.31
    ે
    3.20
    𝑎
    3.20
    𝑢
    3.11
    POSITIVE LOGITS
    sinya
    2.79
    ``
    2.70
    ‥
    2.68
    lık
    2.66
    ydı
    2.62
    ときに
    2.61
    꾼
    2.59
    ภัณฑ์
    2.56
     ".
    2.55
    weiter
    2.52
    Activations Density 0.031%

    No Known Activations