© 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. 120306
    Prev
    Next
    INDEX
    Explanations

    multilingual and connecting words

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

    problems with space, data, or status

    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
    learn
    0.52
    tell
    0.50
     musul
    0.50
    n
    0.49
    cry
    0.47
    supplied
    0.46
    ALWAYS
    0.46
    always
    0.46
    នៅលើ
    0.46
     miserably
    0.46
    POSITIVE LOGITS
    ında
    0.48
    这也是
    0.47
     마치
    0.45
    难以
    0.43
    鹧
    0.43
    ירה
    0.42
    这也
    0.42
     પણ
    0.41
    もあります
    0.41
    感觉到
    0.41
    Activations Density 0.001%

    No Known Activations