© 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. 3447
    Prev
    Next
    INDEX
    Explanations

    Planned Parenthood

    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
    𝗿
    1.77
    𝗲
    1.67
    besiege
    1.54
    िक्रमा
    1.51
    colFirst
    1.48
    𝙧
    1.47
    colLast
    1.44
    ेंट्स
    1.43
    reactivex
    1.42
    purecounter
    1.42
    POSITIVE LOGITS
    os
    1.84
    in
    1.74
    as
    1.59
    al
    1.57
    c
    1.51
    ’
    1.50
    y
    1.48
     And
    1.46
     Much
    1.44
    m
    1.39
    Activations Density 0.071%

    No Known Activations