© 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. 12659
    Prev
    Next
    INDEX
    Explanations

    medical, International, typographic style

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

    recognizing intent or meaning

    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
    ights
    0.52
    ijom
    0.50
    icas
    0.48
    iyas
    0.47
    t
    0.47
    ᄋ
    0.47
    hotels
    0.46
    ript
    0.45
    ওয়
    0.45
    Ms
    0.45
    POSITIVE LOGITS
    面の
    0.50
    捻
    0.48
     excavation
    0.48
     assail
    0.48
     می‌کند
    0.47
    یت
    0.46
     اینکه
    0.46
     ذکر
    0.46
    ニチ
    0.46
     ذہ
    0.46
    Activations Density 0.000%

    No Known Activations