© 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. 32426
    Prev
    Next
    INDEX
    Explanations

    media titles in speculative genres

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on tokens that appear in titles or series names—especially genre-listings or anthology/series names (e.g. “Science Fiction / Horror,” “Tales From The Dark Side,” volume or series labels).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    rido
    -0.79
    lottesville
    -0.75
    mapp
    -0.75
    セット
    -0.72
    jning
    -0.70
    aude
    -0.70
    porus
    -0.70
    marin
    -0.70
    levan
    -0.69
    順
    -0.68
    POSITIVE LOGITS
     Tales
    1.26
    Tales
    1.16
     tales
    1.04
     Presents
    1.03
    tales
    1.00
     suspense
    0.96
     presents
    0.96
     mystery
    0.92
     Science
    0.90
     terror
    0.86
    Activations Density 0.060%

    No Known Activations