© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38843
    Prev
    Next
    INDEX
    Explanations

    skincare, ClassNotFound, getChild, createUser

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

    The neuron activates on mentions of “skin care” (including the single‐word form “skincare”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    *
    -3.83
    (
    -3.63
    2
    -3.09
    F
    -3.03
    \
    -3.03
    8
    -2.97
    an
    -2.92
    7
    -2.91
    I
    -2.88
    +
    -2.86
    POSITIVE LOGITS
    蟜
    2.44
    訛
    2.25
    ⃙
    2.22
     asistente
    2.22
     créativité
    2.20
    zyj
    2.19
     betek
    2.17
    cyj
    2.17
    philosop
    2.16
    爌
    2.16
    Activations Density 0.001%

    No Known Activations