© 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. 3218
    Prev
    Next
    INDEX
    Explanations

    Date elements followed by hyphens

    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
    rzed
    1.55
     강화
    1.50
     labyr
    1.47
    olyb
    1.47
    awać
    1.46
     laz
    1.46
     휘
    1.46
    ąda
    1.45
    哞
    1.44
     hydrostatic
    1.43
    POSITIVE LOGITS
     ا
    1.79
    Things
    1.79
    What
    1.73
    The
    1.67
    things
    1.56
    ‬
    1.56
    of
    1.55
    Eric
    1.55
    This
    1.53
    We
    1.49
    Activations Density 0.148%

    No Known Activations