© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110709
    Prev
    Next
    INDEX
    Explanations

    bone marrow

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

    the word "bone" when used in medical or scientific 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
    fillable
    -0.80
    وروب
    -0.74
     ottobre
    -0.74
    hemiah
    -0.73
     directly
    -0.69
     those
    -0.69
    čili
    -0.68
     Riz
    -0.68
    ("%
    -0.67
     payback
    -0.67
    POSITIVE LOGITS
     bona
    1.05
     fide
    0.94
     father
    0.81
    Controlled
    0.80
     grandsons
    0.78
    males
    0.78
     सद
    0.77
     window
    0.77
     widow
    0.76
    controlled
    0.75
    Activations Density 0.016%

    No Known Activations