© 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. 116572
    Prev
    Next
    INDEX
    Explanations

    horror and death

    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
     smoke
    -1.56
    Smoke
    -1.37
     Smoke
    -1.27
    smoke
    -1.24
     smoked
    -0.96
    烟
    -0.87
    郑
    -0.80
    โพ
    -0.75
     smoky
    -0.74
     smokes
    -0.73
    POSITIVE LOGITS
     چرم
    0.93
     emprender
    0.80
     Texas
    0.78
     chainsaw
    0.78
    Texas
    0.77
     čtyř
    0.77
     esteve
    0.76
    accine
    0.76
     frü
    0.72
    sition
    0.72
    Activations Density 0.017%

    No Known Activations