© 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. 10595
    Prev
    Next
    INDEX
    Explanations

    with or as phrases

    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
    ’
    1.81
     to
    1.62
     have
    1.60
     has
    1.47
     comprehensive
    1.41
     is
    1.41
     in
    1.35
    have
    1.26
     essential
    1.26
     of
    1.25
    POSITIVE LOGITS
     samoglas
    2.56
     کاکروچ
    2.47
     Wochschr
    2.44
    쩝
    2.40
    𐱅
    2.39
     stvar
    2.38
     rotacao
    2.37
    퍁
    2.35
     sowas
    2.34
    +++++++++#
    2.34
    Activations Density 0.161%

    No Known Activations