© 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. 65078
    Prev
    Next
    INDEX
    Explanations

    fibroblast activation and transformation

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

    cells involved in tissue repair and fibrosis, particularly fibroblasts and related cell types in scientific/medical contexts.

    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
    踏み
    -0.81
     diminuer
    -0.80
    strateg
    -0.75
     herr
    -0.75
    컸
    -0.72
    👮
    -0.72
    baar
    -0.72
     salvar
    -0.71
    問合せ
    -0.70
    înt
    -0.69
    POSITIVE LOGITS
     fibroblasts
    1.62
     fibroblast
    1.48
     connective
    1.10
     FAP
    0.86
     remembering
    0.82
    MATRIX
    0.81
     spindle
    0.80
    fib
    0.78
    armes
    0.78
     wound
    0.77
    Activations Density 0.308%

    No Known Activations