© 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. 10398
    Prev
    Next
    INDEX
    Explanations

    asymptomatic (no symptoms)

    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
    sá
    2.79
    ülő
    2.77
    জম
    2.70
     близько
    2.67
    𒆳
    2.60
    sı
    2.59
    чал
    2.56
    s
    2.48
    sst
    2.47
    \;
    2.47
    POSITIVE LOGITS
     E
    1.99
     doby
    1.90
    part
    1.82
     ch
    1.80
     ju
    1.79
    petit
    1.79
    ey
    1.74
    haben
    1.69
     chama
    1.67
    ug
    1.64
    Activations Density 0.000%

    No Known Activations