© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16641
    Prev
    Next
    INDEX
    Explanations

    swimming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    2
    -3.08
    9
    -2.77
    0
    -2.67
    8
    -2.66
    4
    -2.48
    5
    -2.45
    1
    -2.44
    Now
    -2.38
     
    -2.36
    3
    -2.28
    POSITIVE LOGITS
    狲
    2.31
     gada
    2.19
    ㉔
    2.14
    😗
    2.13
     apartament
    2.08
    🥸
    2.06
    躂
    2.06
    нью
    2.05
    tiest
    2.03
    Ꮸ
    2.03
    Activations Density 0.005%

    No Known Activations