© 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. 75922
    Prev
    Next
    INDEX
    Explanations

    Quick links, Impact of, FYI>>>

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

    This neuron detects TV show titles and episode/recap headings.

    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
    muda
    -0.81
     있는
    -0.81
    昂
    -0.80
    ListModule
    -0.74
    屁股
    -0.73
    glück
    -0.73
     sawing
    -0.71
    Egyptian
    -0.71
    .__
    -0.70
     Rude
    -0.69
    POSITIVE LOGITS
     Permalink
    0.92
     nivel
    0.88
    validators
    0.79
     Sanctuary
    0.77
     вс
    0.76
     Reserva
    0.75
    üler
    0.74
    醛
    0.73
    それで
    0.71
     sartén
    0.71
    Activations Density 0.001%

    No Known Activations