© 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. 89945
    Prev
    Next
    INDEX
    Explanations

    free software; redistribute/modify

    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
     Debra
    -0.80
     元
    -0.78
    ว่าง
    -0.72
    Debra
    -0.71
    勉強
    -0.70
     Riding
    -0.67
    Acab
    -0.65
    Abit
    -0.64
    rob
    -0.63
    Rispondi
    -0.63
    POSITIVE LOGITS
    usec
    0.84
    DataOutputStream
    0.81
    ardless
    0.72
    wisata
    0.71
    鯱
    0.69
     ça
    0.69
    coun
    0.69
    toff
    0.69
     OFF
    0.68
    IPP
    0.67
    Activations Density 0.065%

    No Known Activations