© 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. 13020
    Prev
    Next
    INDEX
    Explanations

    our or this or your

    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
     भाषाओं
    2.32
    㖮
    2.26
    㳚
    2.17
    㑒
    2.17
    ꗠ
    2.16
     ईमित्र
    2.15
    砳
    2.15
    ⿹
    2.15
    㞔
    2.14
    㞒
    2.14
    POSITIVE LOGITS
    ,
    1.39
    ides
    1.39
    ring
    1.38
    1
    1.37
    m
    1.29
    ্গ
    1.29
     ,
    1.27
    -
    1.26
    cons
    1.26
    ifier
    1.24
    Activations Density 0.073%

    No Known Activations