© 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. 9019
    Prev
    Next
    INDEX
    Explanations

    common negations starting with Not

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

    not just but

    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
    legten
    0.39
     ਅਤੇ
    0.38
     فونبټ
    0.38
     və
    0.37
     nimmt
    0.36
     және
    0.35
    ologici
    0.33
     ۽
    0.33
     krijgt
    0.33
    zeme
    0.33
    POSITIVE LOGITS
     a
    0.56
     in
    0.52
     as
    0.45
    s
    0.38
     only
    0.37
     an
    0.37
     not
    0.36
    A
    0.36
     on
    0.34
     one
    0.34
    Activations Density 0.152%

    No Known Activations