© 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. 34-GEMMASCOPE-RES-131K
    4. 119062
    Prev
    Next
    INDEX
    Explanations

    Names in legal documents

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    fele
    -0.76
    ੜ
    -0.74
    ciated
    -0.74
    Ket
    -0.73
     pri
    -0.72
     IconButton
    -0.71
    zx
    -0.70
    Nea
    -0.69
     Attorney
    -0.69
    álisis
    -0.68
    POSITIVE LOGITS
    Sylvia
    0.78
    ᗴ
    0.73
    对此
    0.72
     Sylvia
    0.72
     Dumont
    0.71
    一切
    0.70
    Krok
    0.70
    য়
    0.68
     leveled
    0.68
    
    0.68
    Activations Density 0.043%

    No Known Activations