© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111153
    Prev
    Next
    INDEX
    Explanations

    prognostic impact factors

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

    This neuron detects the word "prognostic" and related terms in medical research 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_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
    蔸
    -2.94
    硖
    -2.94
    髣
    -2.86
    嗄
    -2.80
    觏
    -2.70
    pinephrine
    -2.61
    螄
    -2.61
    佾
    -2.59
     zijne
    -2.56
     louer
    -2.55
    POSITIVE LOGITS
    ing
    3.92
    2
    3.38
    –
    3.02
    -
    2.84
    4
    2.83
    In
    2.73
    より
    2.69
    '
    2.67
    7
    2.56
     
    2.53
    Activations Density 0.012%

    No Known Activations