© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7915
    Prev
    Next
    INDEX
    Explanations

    sudden passing, administering cl, disposed in

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

    physical positioning or placement relationships like "in", "on", "between" or "of" especially when describing technical arrangements.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Not in Any Lists

    No Comments

    Negative Logits
     three
    -2.17
     after
    -1.91
     at
    -1.91
     through
    -1.91
     every
    -1.84
     two
    -1.81
     now
    -1.80
     seven
    -1.77
     still
    -1.72
     five
    -1.72
    POSITIVE LOGITS
     créer
    1.77
    鼉
    1.76
    來
    1.73
    鳚
    1.71
     Dinas
    1.70
     ส์
    1.70
    傒
    1.69
    乁
    1.65
     zoude
    1.64
    了
    1.63
    Activations Density 0.223%

    No Known Activations