© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 27130
    Prev
    Next
    INDEX
    Explanations

    acronyms for business and technical terms

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

    acronyms in tech and data

    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
    ic
    0.61
    im
    0.58
    estrut
    0.57
    g
    0.57
    et
    0.55
    ap
    0.54
    el
    0.53
    dag
    0.53
    f
    0.52
    day
    0.52
    POSITIVE LOGITS
    有助于
    0.50
    ăz
    0.48
    🎾
    0.46
    용한
    0.43
    🔬
    0.43
     onların
    0.42
    他们在
    0.41
    됩니다
    0.41
     činjen
    0.41
     antibodies
    0.41
    Activations Density 0.037%

    No Known Activations