© 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. 11990
    Prev
    Next
    INDEX
    Explanations

    what to extent

    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
    𝗮
    2.41
    َّا
    2.32
    `<
    2.27
    𝘂
    2.22
    𝗿
    2.11
     ràng
    2.10
    𝗰
    2.04
    𝗲
    2.04
    AppBsky
    2.02
    𝗱
    2.01
    POSITIVE LOGITS
    and
    2.79
     is
    2.45
     was
    2.37
     è
    2.35
     has
    2.31
    ist
    2.28
    は
    2.27
     and
    2.27
     és
    2.26
    お
    2.23
    Activations Density 0.040%

    No Known Activations