© 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-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 451
    Prev
    Next
    INDEX
    Explanations

    changing technology or improvements

    np_acts-logits-general · gemini-2.5-flash-lite

    modifying attention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_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
    1
    0.88
    6
    0.84
    </h2>
    0.79
    that
    0.78
    5
    0.76
    </h5>
    0.71
    4
    0.71
    of
    0.71
     are
    0.69
    </strong>
    0.67
    POSITIVE LOGITS
    ر
    1.20
    u
    0.91
    ו
    0.89
    л
    0.84
    o
    0.81
    ل
    0.79
    uia
    0.77
    tól
    0.77
    ar
    0.73
    in
    0.71
    Activations Density 1.934%

    No Known Activations