© 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. 10885
    Prev
    Next
    INDEX
    Explanations

    determining what

    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
    s
    5.48
    ات
    3.67
    ים
    3.56
    sene
    3.40
    orul
    3.29
    sion
    3.23
    sers
    3.20
    ا
    3.16
    sberg
    3.09
    sø
    3.09
    POSITIVE LOGITS
    ھی
    3.08
    క్కువ
    2.76
    ক্ষণ
    2.74
    uning
    2.69
    𝙍
    2.66
    ्रे
    2.64
    𝙇
    2.63
     ballon
    2.61
    𝐠
    2.61
    ly
    2.60
    Activations Density 0.017%

    No Known Activations