© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76893
    Prev
    Next
    INDEX
    Explanations

    The Sandman comics

    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
    AppId
    -0.80
    饭
    -0.76
     Kampala
    -0.76
    maxcdn
    -0.72
     maioria
    -0.71
    technik
    -0.71
     australis
    -0.70
    电影
    -0.69
    邃
    -0.68
    awakeFromNib
    -0.68
    POSITIVE LOGITS
     Vertigo
    0.95
     Sandman
    0.94
     Endless
    0.94
     Constantine
    0.93
     Luci
    0.88
    тропо
    0.82
     Mor
    0.78
     SAND
    0.76
     Desire
    0.73
    Sand
    0.73
    Activations Density 0.011%

    No Known Activations