© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10258
    Prev
    Next
    INDEX
    Explanations

    eight zeroes

    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
    Negative Logits
     αργ
    1.89
     Lista
    1.78
     berfungsi
    1.75
    “
    1.75
     equivale
    1.74
     liga
    1.72
     Applicable
    1.66
    <0x1E>
    1.66
     Agenda
    1.65
    feasible
    1.62
    POSITIVE LOGITS
     breech
    1.32
    ecal
    1.23
     adorable
    1.20
    eyJ
    1.16
     daugiau
    1.14
     бъдат
    1.13
    eby
    1.12
    aaaa
    1.08
    inink
    1.07
    eer
    1.07
    Activations Density 0.018%

    No Known Activations