© 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. 371
    Prev
    Next
    INDEX
    Explanations

    Great law license

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

    The neuron fires on fashion/celebrity style descriptions emphasizing body features (e.g. cleavage and curves).

    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
     our
    -1.20
     додат
    -1.15
    områ
    -1.14
     we
    -1.08
    ־ה
    -1.04
    なのです
    -1.03
    Says
    -1.02
     this
    -1.02
     ':'
    -0.98
     suv
    -0.97
    POSITIVE LOGITS
     Independiente
    1.13
     alemão
    1.05
     divul
    1.02
     invá
    1.01
    ις
    1.00
    膣
    1.00
     eixo
    1.00
    zków
    0.99
     oči
    0.98
    秶
    0.98
    Activations Density 0.001%

    No Known Activations