© 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. 10-GEMMASCOPE-RES-131K
    7. 85549
    Prev
    Next
    INDEX
    Explanations

    FGF receptor growth factor

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

    references to growth factors, especially FGF (fibroblast growth factor).

    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_10/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
     all
    -2.20
    //
    -1.98
     fierce
    -1.95
     three
    -1.91
     even
    -1.85
     funcional
    -1.82
    滙
    -1.78
     Who
    -1.77
     TWO
    -1.77
     Also
    -1.75
    POSITIVE LOGITS
    猛然
    2.06
    髫
    1.98
     is
    1.93
     ☺️
    1.89
    ፨
    1.82
     arrêter
    1.80
    ꯵
    1.79
    ſſen
    1.78
     ジップ
    1.76
     小型
    1.74
    Activations Density 0.036%

    No Known Activations