© 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. 117255
    Prev
    Next
    INDEX
    Explanations

    type IV collagen or MMP

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

    terminology related to matrix metalloproteinases and collagen in scientific/medical texts.

    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
     camisas
    -0.77
    ơm
    -0.72
    Homo
    -0.67
    делы
    -0.67
     gesprochen
    -0.66
     mills
    -0.66
    Ị
    -0.66
     Ryd
    -0.66
    abend
    -0.65
    liest
    -0.65
    POSITIVE LOGITS
     gelatin
    3.48
     collagen
    3.11
     Gelatin
    2.69
     Collagen
    2.52
    gel
    1.93
    Gel
    1.91
     gelatina
    1.91
     gel
    1.90
    col
    1.72
    Col
    1.72
    Activations Density 0.082%

    No Known Activations