© 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. 34-GEMMASCOPE-RES-131K
    7. 3666
    Prev
    Next
    INDEX
    Explanations

    division and separation

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

    concepts related to division or dividing things into parts or categories.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    fibra
    -1.01
    diffic
    -0.95
    discre
    -0.93
    匐
    -0.93
    ernacle
    -0.90
     Zwie
    -0.90
     leitor
    -0.90
     despicable
    -0.88
     výbě
    -0.85
    変換
    -0.84
    POSITIVE LOGITS
     into
    1.48
     between
    1.34
     между
    1.07
     among
    0.95
    waters
    0.87
    __':
    0.85
    ными
    0.84
     honors
    0.84
     asunder
    0.84
     maternelle
    0.83
    Activations Density 0.032%

    No Known Activations