© 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. 3252
    Prev
    Next
    INDEX
    Explanations

    complex calculations and collections

    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
    eken
    2.56
    sinya
    2.53
    辕
    2.52
    SHRI
    2.47
    畊
    2.45
    icrob
    2.42
    दशी
    2.33
    ]".
    2.29
    agles
    2.28
    cesor
    2.26
    POSITIVE LOGITS
    es
    3.54
    an
    3.50
    u
    3.31
    ي
    3.30
    า
    3.23
    ೆ
    3.21
    as
    3.12
    ة
    3.12
    ය
    3.09
    ar
    3.00
    Activations Density 0.037%

    No Known Activations