© 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. 47489
    Prev
    Next
    INDEX
    Explanations

    Montserrat, Meningioma, immunology, php, London

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

    references to Montserrat, which appears to be either a place, monastery, or religious institution.

    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
    culum
    -0.86
    Workbench
    -0.78
    occuper
    -0.78
    OSIS
    -0.76
    ativní
    -0.75
    猫咪
    -0.74
    зидент
    -0.74
     стороне
    -0.74
    ACIONAL
    -0.74
     Bobo
    -0.73
    POSITIVE LOGITS
     Montserrat
    1.09
    Montserrat
    1.00
     admis
    0.78
     cri
    0.71
    グロー
    0.68
     Pr
    0.68
    Bergen
    0.68
     مصرى
    0.68
     Waterford
    0.66
    icam
    0.65
    Activations Density 0.009%

    No Known Activations