© 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. 22-GEMMASCOPE-RES-131K
    7. 14808
    Prev
    Next
    INDEX
    Explanations

    dry and sensitive skin/hair

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

    descriptors of skin, hair, or body conditions (particularly focusing on dryness, sensitivity, or specific conditions).

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

    The neuron is detecting mentions of skin and hair‐care conditions and types (e.g. “skin,” “hair,” “dry,” “damaged,” “sensitive,” “type,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    brtc
    -1.39
     веке
    -1.34
    ViewChild
    -1.32
     it
    -1.20
    element
    -1.19
    acionales
    -1.09
    mil
    -1.09
     sarili
    -1.08
    iibo
    -1.07
     السياس
    -1.06
    POSITIVE LOGITS
    ÜN
    1.34
     problémy
    1.33
    ἵ
    1.32
    ׇ
    1.23
     ganchillo
    1.19
    ต้องการ
    1.15
     kategorii
    1.14
    Karakter
    1.14
     cukru
    1.13
     Publicar
    1.13
    Activations Density 0.009%

    No Known Activations