© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 12897
    Prev
    Next
    INDEX
    Explanations

    Gettysburg, Goblin, Ground Beef

    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
    गु
    2.71
    潢
    2.59
    elves
    2.56
    vasser
    2.41
     enquête
    2.41
    ښت
    2.37
    젬
    2.33
    ming
    2.31
     bing
    2.30
    atlan
    2.28
    POSITIVE LOGITS
    ‌ನಲ್ಲಿ
    2.90
    त्रेयी
    2.70
    ଥ
    2.63
    ‌ನ
    2.48
    schap
    2.46
     Gł
    2.41
    мпаваць
    2.38
     hazırl
    2.35
     pity
    2.34
     Con
    2.34
    Activations Density 0.023%

    No Known Activations