© 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. 22-GEMMASCOPE-RES-131K
    7. 68634
    Prev
    Next
    INDEX
    Explanations

    skin and related conditions

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

    This neuron activates for references to skin and dermatological terms in medical and 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_22/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
     It
    -2.70
    al
    -2.52
    s
    -2.45
     Also
    -2.45
    It
    -2.45
    es
    -2.27
    As
    -2.27
     
    -2.13
    $
    -2.11
    が見える
    -2.08
    POSITIVE LOGITS
     帅气
    2.58
    ৹
    2.53
    ᕕ
    2.38
    
    2.38
    sepatu
    2.36
    italien
    2.31
    ୌ
    2.25
    namentales
    2.25
    薺
    2.20
     continúas
    2.19
    Activations Density 0.026%

    No Known Activations