© 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. 2812
    Prev
    Next
    INDEX
    Explanations

    tailoring or customization

    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
    imli
    2.67
    imi
    2.66
    ╴
    2.48
    "-------
    2.45
    ೋತಿ
    2.45
     memer
    2.43
    nse
    2.42
     Teh
    2.41
    стина
    2.41
     टोक
    2.39
    POSITIVE LOGITS
    ᐟ
    3.97
    htaccess
    2.87
    ization
    2.57
    <bos>
    2.42
    CommandBuffer
    2.35
    PHONY
    2.34
    a
    2.33
    od
    2.18
    addGap
    2.13
    ood
    2.09
    Activations Density 0.078%

    No Known Activations