© 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. 154767
    Prev
    Next
    INDEX
    Explanations

    outdoor, activities

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

    contrast, but, list items

    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
     Valent
    0.49
    我觉得
    0.47
     família
    0.46
     серьез
    0.46
    统治
    0.45
     ребен
    0.45
     счастли
    0.44
    ง
    0.44
    几年
    0.44
    我已经
    0.44
    POSITIVE LOGITS
     but
    0.74
    but
    0.67
     ولكن
    0.60
     لیکن
    0.58
     mutta
    0.56
    conference
    0.56
     multidis
    0.54
     ngunit
    0.53
     maar
    0.53
    .\\
    0.53
    Activations Density 0.001%

    No Known Activations