© 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. 2054
    Prev
    Next
    INDEX
    Explanations

    AI disclaimers and introductory statements

    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
    ヨタ
    2.79
     +:+
    2.69
    ोत्तर
    2.68
     cmake
    2.64
    彡
    2.63
    yczne
    2.53
    ことで
    2.53
    levision
    2.51
    cionario
    2.51
    ৗ
    2.48
    POSITIVE LOGITS
     пользователя
    2.45
    دا
    2.05
     churning
    2.04
    داً
    2.04
    teller
    1.99
     melting
    1.96
     Locker
    1.95
    ंध्र
    1.93
     haunt
    1.92
     keeper
    1.90
    Activations Density 0.073%

    No Known Activations