© 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. 64741
    Prev
    Next
    INDEX
    Explanations

    National Scripps Geriatric health inhibition

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

    text formatting or structural elements in various types of documents and code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron spotlights itinerary “headings” – namely times (e.g. “08h30”, “09h30”) and key place/attraction names (e.g. “town”, “the National Oceanographic Institute”, “sea creatures”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    囃
    -0.79
     Courant
    -0.70
    beo
    -0.69
     日期
    -0.68
    ريات
    -0.68
    ﺓ
    -0.66
    queria
    -0.66
     textStatus
    -0.66
     Polka
    -0.66
     Impro
    -0.66
    POSITIVE LOGITS
    ages
    0.82
    cinogen
    0.77
     Damascus
    0.75
    zeć
    0.75
    QY
    0.73
    titious
    0.73
     CY
    0.73
     اینجا
    0.72
    gy
    0.70
     autrefois
    0.70
    Activations Density 0.012%

    No Known Activations