© 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. 34-GEMMASCOPE-RES-131K
    7. 78795
    Prev
    Next
    INDEX
    Explanations

    scientific terms and labels

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

    scientific and technical terminology in physics and particle physics papers.

    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_34/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
     pubblica
    -0.81
    cils
    -0.79
     PHY
    -0.79
     અને
    -0.78
    擱
    -0.77
    Acad
    -0.75
    苓
    -0.75
     Stras
    -0.75
    Forza
    -0.75
     CSE
    -0.75
    POSITIVE LOGITS
     knocked
    0.75
    asants
    0.74
     तुल
    0.73
     shadowed
    0.71
    messi
    0.71
    moves
    0.69
    rover
    0.68
    Rujuakan
    0.67
    aknya
    0.67
     Medium
    0.67
    Activations Density 0.030%

    No Known Activations