© 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. 34-GEMMASCOPE-RES-131K
    7. 109296
    Prev
    Next
    INDEX
    Explanations

    towel washcloths

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

    The neuron activates on mentions of towels or similar fabric items (e.g. “towel,” “towels,” “beach towels,” “wash cloths”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     ω
    -0.76
    irmar
    -0.75
    Boxes
    -0.73
     Wikidata
    -0.71
    AFF
    -0.71
     ACP
    -0.70
    NVIC
    -0.69
     зали
    -0.69
     教室
    -0.66
    ICD
    -0.65
    POSITIVE LOGITS
     towels
    3.23
     towel
    2.97
     Towel
    2.41
     Towels
    2.27
    Tow
    1.81
    タオル
    1.59
     terry
    1.54
    tow
    1.41
     toalla
    1.35
     TOW
    1.30
    Activations Density 0.014%

    No Known Activations