© 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. 3873
    Prev
    Next
    INDEX
    Explanations

    nasal

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

    The neuron detects anatomical terms related to the nasal region, particularly the word "nasal" and variants of "sinus/paranasal".

    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
     Then
    -2.94
    前来
    -2.69
    苙
    -2.64
    をしている
    -2.58
     terrific
    -2.53
    푔
    -2.52
    好みの
    -2.52
    笵
    -2.48
    迨
    -2.48
    䊏
    -2.48
    POSITIVE LOGITS
    e
    2.97
    s
    2.95
    when
    2.73
    }$
    2.72
    When
    2.55
    They
    2.33
    '
    2.33
     When
    2.33
    These
    2.31
    <td>
    2.23
    Activations Density 0.011%

    No Known Activations