© 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. 12855
    Prev
    Next
    INDEX
    Explanations

    comma after specific words

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

    commas

    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
    ంతా
    0.55
     ষে
    0.53
    際に
    0.52
     लीजिएगा
    0.52
    <unused2223>
    0.50
     தனிநாயகம்
    0.50
    =")
    0.49
    لقة
    0.49
     પટે
    0.49
    ="))
    0.49
    POSITIVE LOGITS
    ،
    2.47
    ，
    2.17
    ,
    2.13
    ၊
    2.02
    ፣
    1.77
    、
    1.70
     ,
    1.63
    ,,
    1.62
     ،
    1.56
     ፣
    1.56
    Activations Density 0.253%

    No Known Activations