© 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. 48496
    Prev
    Next
    INDEX
    Explanations

    biological transcription and cell division

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

    biological and molecular structures in scientific text, particularly related to chromosomes and cellular components.

    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
    Soccer
    -0.69
    假日
    -0.67
     Guille
    -0.67
     nervousness
    -0.66
     Pâ
    -0.66
     Inex
    -0.66
     tủ
    -0.65
    合せ
    -0.64
     rejected
    -0.64
    matched
    -0.64
    POSITIVE LOGITS
     insulation
    1.21
     Insulation
    1.20
     contacts
    1.07
    contacts
    0.95
     contact
    0.95
    contact
    0.94
    Contacts
    0.91
     Contacts
    0.90
     insulated
    0.89
    Contact
    0.88
    Activations Density 0.031%

    No Known Activations