© 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. 99144
    Prev
    Next
    INDEX
    Explanations

    traveler reviews, tomography, multilingual

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

    priorities and suggestions

    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
    BOARD
    0.47
    ด
    0.46
     keys
    0.45
    NAS
    0.43
    KEYS
    0.43
    HAM
    0.43
    स्करण
    0.43
     Aze
    0.43
    「
    0.43
    al
    0.43
    POSITIVE LOGITS
     Кан
    0.54
     дет
    0.54
     جميلة
    0.54
     बच्चों
    0.53
     เด็ก
    0.50
     اكثر
    0.50
     детям
    0.50
    珼
    0.50
     disgusted
    0.49
     दमदार
    0.49
    Activations Density 0.000%

    No Known Activations