© 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. 11952
    Prev
    Next
    INDEX
    Explanations

    the sacred, profane, new, simple, past

    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
     البلد
    -0.86
     of
    -0.84
     Иван
    -0.84
    GLuint
    -0.82
     speciale
    -0.79
     drit
    -0.79
     آمریک
    -0.77
    Xiao
    -0.76
     Almeida
    -0.76
    del
    -0.75
    POSITIVE LOGITS
     mundane
    1.31
     Sublime
    1.22
     profane
    1.20
     unknown
    1.07
     extraordinary
    1.07
     unexpected
    1.06
     sublime
    1.05
     unusual
    1.03
     purely
    0.98
     commonplace
    0.98
    Activations Density 0.025%

    No Known Activations