© 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. 64635
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and enumeration

    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
    Not in Any Lists

    No Comments

    Negative Logits
    וּ
    -1.23
     their
    -1.22
    szy
    -1.19
    Nachteile
    -1.18
     on
    -1.16
    Among
    -1.15
     operar
    -1.13
     soñar
    -1.13
     new
    -1.12
     berpeng
    -1.12
    POSITIVE LOGITS
    なども
    1.15
    などを
    1.15
    などが
    1.12
    Эзоҳ
    1.00
     レイ
    0.95
    と
    0.95
    などは
    0.94
    and
    0.94
    ;,
    0.93
     ,'
    0.93
    Activations Density 0.005%

    No Known Activations