© 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. 67189
    Prev
    Next
    INDEX
    Explanations

    pluralizing with parentheses

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

    plural abbreviations

    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
    hauses
    0.51
    数组
    0.49
    粒子
    0.49
     UserController
    0.48
    ᱞ
    0.48
    毫米
    0.46
    క్కడ
    0.46
    িরের
    0.46
    rogens
    0.46
    াত্ত
    0.45
    POSITIVE LOGITS
    and
    0.66
    re
    0.66
    a
    0.64
    have
    0.60
    in
    0.58
    an
    0.58
    tion
    0.57
     சுமார்
    0.56
    ir
    0.55
    i
    0.55
    Activations Density 0.005%

    No Known Activations