© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 142457
    Prev
    Next
    INDEX
    Explanations

    function verbs and nouns

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

    explaining without endorsing

    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
     LaTeX
    0.52
    points
    0.50
    هایی
    0.50
    and
    0.48
    ๆ
    0.48
    applicable
    0.48
     manipulate
    0.47
     curricular
    0.47
     KYC
    0.47
    ี
    0.47
    POSITIVE LOGITS
     അതേ
    0.47
     만드는
    0.43
     vyl
    0.43
    嗓
    0.43
     يم
    0.43
    ي
    0.40
     überras
    0.40
     ক্লো
    0.39
     普通
    0.39
    飽
    0.39
    Activations Density 0.001%

    No Known Activations