© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57699
    Prev
    Next
    INDEX
    Explanations

    fairy tale narratives

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

    The neuron strongly activates on quoted movie titles or similar media names (and adjoining metadata like quotes or age mentions).

    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
    Sidenav
    -0.77
    hira
    -0.76
    gx
    -0.74
     Poliz
    -0.73
    コー
    -0.72
    стра
    -0.72
     caffè
    -0.71
    tifiz
    -0.71
     mussten
    -0.71
    掖
    -0.70
    POSITIVE LOGITS
     Cinderella
    2.03
    Cinderella
    1.86
     cinder
    1.11
    rags
    1.10
     rags
    1.05
     slipper
    1.00
     pumpkins
    0.97
     pumpkin
    0.95
     stepmother
    0.92
    inderella
    0.91
    Activations Density 0.004%

    No Known Activations