© 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. 10-GEMMASCOPE-RES-131K
    7. 131003
    Prev
    Next
    INDEX
    Explanations

    polytica, ica, IA

    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_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
     if
    -2.45
     to
    -2.36
     when
    -1.72
    when
    -1.53
     когато
    -1.48
    larınız
    -1.48
     عندما
    -1.45
     czarny
    -1.43
     or
    -1.42
     quando
    -1.38
    POSITIVE LOGITS
     diamantes
    1.91
     veda
    1.77
     lampa
    1.76
     tramontina
    1.75
     bambu
    1.73
    ться
    1.68
     vinil
    1.68
     gita
    1.65
     diamant
    1.63
     felpa
    1.59
    Activations Density 0.209%

    No Known Activations