© 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. 2831
    Prev
    Next
    INDEX
    Explanations

    fascinating and increasingly

    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
    ings
    2.58
    sworth
    2.50
    working
    2.42
    ী
    2.31
    stead
    2.30
    ธ์
    2.25
    giving
    2.20
    holtz
    2.19
    thood
    2.16
    ijiet
    2.15
    POSITIVE LOGITS
    DEFGHIJKLMNOP
    3.45
    sí
    3.45
    s
    3.41
    ਆਂ
    3.15
    鹉
    2.92
    dır
    2.91
    sini
    2.90
    sı
    2.88
    ség
    2.78
    ات
    2.76
    Activations Density 0.098%

    No Known Activations