© 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. 31-GEMMASCOPE-2-RES-262K
    7. 137437
    Prev
    Next
    INDEX
    Explanations

    Quite a

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

    quite and intensifiers

    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_31_width_262k_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
    ↵↵
    0.93
    <h3>
    0.92
    ג
    0.87
    ी
    0.83
    <h2>
    0.82
     (
    0.82
     प्रक्रिया
    0.82
    ’
    0.82
    iest
    0.79
     is
    0.75
    POSITIVE LOGITS
    in
    1.22
    on
    1.16
    an
    1.14
    ١
    1.09
     a
    1.08
    at
    1.07
    ان
    1.05
    на
    1.02
    as
    1.00
    c
    0.98
    Activations Density 0.020%

    No Known Activations