© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 120012
    Prev
    Next
    INDEX
    Explanations

    css properties and layout attributes

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

    CSS properties that specify left-side spacing (padding-left, margin-left, border-left).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     things
    -1.81
     ""],
    -1.57
    i
    -1.54
     οπο
    -1.54
    ありますが
    -1.52
    ed
    -1.50
     tyres
    -1.49
    意思是
    -1.48
     utilise
    -1.46
    amemnon
    -1.46
    POSITIVE LOGITS
    眛
    1.84
    Ꮀ
    1.80
     obcí
    1.78
    龗
    1.73
    骘
    1.71
    rechts
    1.70
     fueran
    1.63
    跸
    1.63
    猡
    1.62
    皝
    1.62
    Activations Density 0.001%

    No Known Activations