© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1694
    Prev
    Next
    INDEX
    Explanations

    background, sexual history, in vitro

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

    code and technical content with indentation and formatting patterns.

    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
     автор
    -0.81
    temming
    -0.80
     pricing
    -0.78
     commande
    -0.77
     entities
    -0.75
    精灵
    -0.75
     sterile
    -0.75
     résult
    -0.75
     covid
    -0.73
     DM
    -0.72
    POSITIVE LOGITS
     sacco
    0.84
     OTHER
    0.81
     Anggota
    0.79
    memberId
    0.78
    Constitution
    0.78
    nicos
    0.77
    Vehiculo
    0.75
     memberId
    0.75
     villaggio
    0.75
     dues
    0.75
    Activations Density 0.001%

    No Known Activations