© 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. 10-GEMMASCOPE-RES-131K
    7. 114025
    Prev
    Next
    INDEX
    Explanations

    offer, sides, sparring, treat, perspective, haircut, leads, publisher

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    此外
    -1.46
    队友
    -1.33
    🧫
    -1.31
     jaro
    -1.30
    回到了
    -1.30
    tdessen
    -1.29
    惋
    -1.29
    now
    -1.29
     endforeach
    -1.28
     gena
    -1.28
    POSITIVE LOGITS
     or
    2.28
    หรือ
    1.70
    𝗼
    1.58
    𝗺
    1.52
     the
    1.50
     یا
    1.46
    fruta
    1.44
    archiviato
    1.42
    начала
    1.40
     ersten
    1.35
    Activations Density 0.203%

    No Known Activations