© 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. 41697
    Prev
    Next
    INDEX
    Explanations

    negation followed by verbs

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

    mosaic motif

    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
     जरिए
    0.50
     مكت
    0.49
     선생님
    0.48
     शुरूआत
    0.48
     Cancel
    0.47
     청바
    0.46
     좌표
    0.46
     캠
    0.46
     Frühstück
    0.46
     கட்டிட
    0.46
    POSITIVE LOGITS
     pathogenicity
    0.57
    AllFilesIn
    0.55
    פל
    0.52
     asterisk
    0.51
    ৫
    0.49
     intruders
    0.48
    ಐ
    0.46
     allegiance
    0.45
    มาชิก
    0.45
     onlook
    0.44
    Activations Density 0.000%

    No Known Activations