© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12322
    Prev
    Next
    INDEX
    Explanations

    hang heavy or thick

    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
    تش
    3.14
    ר
    3.13
    læ
    2.94
    либ
    2.91
    न
    2.91
    onuclease
    2.90
    н
    2.85
    нский
    2.84
    afe
    2.76
    lot
    2.71
    POSITIVE LOGITS
    th
    2.71
     bety
    2.64
     leth
    2.57
    ுகள்
    2.55
     ύ
    2.54
    ভাবে
    2.52
    renched
    2.52
    тріш
    2.52
    helial
    2.47
    সব
    2.47
    Activations Density 0.007%

    No Known Activations