© 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. 22-GEMMASCOPE-RES-131K
    7. 34503
    Prev
    Next
    INDEX
    Explanations

    television show or program

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

    The neuron responds to words and phrases related to television broadcasting (e.g. program titles, presentation verbs like “presented” or “broadcast,” and show-related terminology).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     to
    -1.34
    L
    -1.25
    H
    -1.16
     disposiciones
    -1.14
    lysses
    -1.13
    k
    -1.10
    V
    -1.10
     L
    -1.10
    G
    -1.09
     $
    -1.07
    POSITIVE LOGITS
     weekly
    1.84
    Ayrıca
    1.64
     semanal
    1.62
     guantes
    1.43
     plages
    1.39
     esquí
    1.38
     appartement
    1.35
     remé
    1.34
     sáb
    1.32
     potensi
    1.31
    Activations Density 0.075%

    No Known Activations