© 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. 103108
    Prev
    Next
    INDEX
    Explanations

    configuration directives

    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
    変化
    -0.78
    tors
    -0.71
     bili
    -0.69
    ILLA
    -0.69
    pach
    -0.68
    Pup
    -0.68
     Signore
    -0.68
     Sedgwick
    -0.67
     Nachweis
    -0.67
    ZIONE
    -0.67
    POSITIVE LOGITS
     welchem
    0.78
     ર
    0.73
     Play
    0.73
    issons
    0.72
     servir
    0.67
    maru
    0.66
    står
    0.66
    лива
    0.66
    σιν
    0.66
    èze
    0.66
    Activations Density 0.077%

    No Known Activations