© 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. 7400
    Prev
    Next
    INDEX
    Explanations

    compound nouns and phrases

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

    identifying list items and structure

    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
    ೆಯಿಂದ
    0.38
     Riemannian
    0.38
    ֖
    0.37
     intramolecular
    0.37
     discarding
    0.36
     downregulated
    0.35
     intravenously
    0.35
     matplotlib
    0.35
     QUERY
    0.35
     második
    0.35
    POSITIVE LOGITS
     و
    0.70
    ،
    0.63
     &
    0.61
     и
    0.60
    、
    0.59
     ,
    0.59
    ®,
    0.56
    ፣
    0.56
     và
    0.55
    ၊
    0.54
    Activations Density 0.178%

    No Known Activations