© 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. 210450
    Prev
    Next
    INDEX
    Explanations

    yourself then

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

    documentation explaining code

    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
    8
    0.61
    6
    0.61
    x
    0.59
    4
    0.59
    b
    0.58
    -
    0.58
    5
    0.57
    /
    0.56
     and
    0.54
    =
    0.54
    POSITIVE LOGITS
    㷫
    0.48
     ಭಯ
    0.45
    㞓
    0.44
    ObjectUnderTest
    0.44
     elektromagnet
    0.44
     जिसको
    0.43
    チック
    0.43
    
    0.41
     notificações
    0.41
    屇
    0.41
    Activations Density 0.001%

    No Known Activations