© 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. 7-GEMMASCOPE-2-RES-16K
    7. 1832
    Prev
    Next
    INDEX
    Explanations

    wash, least, Valley

    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
    𝑢
    3.42
    𝑠
    3.15
    𝕚
    2.90
    a
    2.89
    𝑒
    2.82
    েমনি
    2.74
    ድረግ
    2.71
    鐒
    2.70
    𝙄
    2.69
    kses
    2.68
    POSITIVE LOGITS
    t
    3.42
    री
    3.14
    tog
    3.04
    h
    2.79
    कुंठ
    2.67
    ன்
    2.64
    ่
    2.55
    tint
    2.53
    l
    2.51
    lisher
    2.44
    Activations Density 1.314%

    No Known Activations