© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3696
    Prev
    Next
    INDEX
    Explanations

    code snippets and configuration

    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
     teased
    2.19
    TE
    2.15
    RA
    2.09
    ڈ
    2.00
    wadi
    1.99
    Hg
    1.99
    ওনা
    1.91
    rave
    1.91
    arnish
    1.88
    िव
    1.88
    POSITIVE LOGITS
    s
    3.51
    t
    3.43
    溂
    3.33
    मर्रा
    3.16
    т
    2.99
    dır
    2.99
    sá
    2.91
    tım
    2.87
    ness
    2.84
    ‌ترین
    2.84
    Activations Density 0.132%

    No Known Activations