© 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. 15715
    Prev
    Next
    INDEX
    Explanations

    words starting with 'be' or 'beloved'

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

    be or be-like sounds

    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
     forgery
    0.52
    䇞
    0.50
     excelencia
    0.49
    स्फोट
    0.47
    તમ
    0.46
    不需要
    0.46
    多次
    0.46
    ንዳንድ
    0.46
    吸收
    0.45
    जेक्ट
    0.45
    POSITIVE LOGITS
    Be
    0.67
     BE
    0.67
     ബെ
    0.58
     เบ
    0.55
     베
    0.55
     बे
    0.54
    autiful
    0.54
     ベ
    0.54
     Be
    0.53
    BE
    0.52
    Activations Density 0.054%

    No Known Activations