© 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. 81495
    Prev
    Next
    INDEX
    Explanations

    potential changes

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

    unsettling tourist descriptions

    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
    用了
    0.45
    ចាំ
    0.44
    multiplier
    0.43
    先前
    0.43
    磴
    0.41
    预期
    0.41
    焦虑
    0.41
    मोहन
    0.41
    udar
    0.41
    迢
    0.40
    POSITIVE LOGITS
     neuest
    0.53
     홍
    0.50
     diesen
    0.49
     reichen
    0.49
     criminal
    0.47
     gering
    0.46
     రాష్ట్ర
    0.46
     gato
    0.46
     adecuado
    0.46
     geeign
    0.46
    Activations Density 0.001%

    No Known Activations