© 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. 10-GEMMASCOPE-RES-131K
    7. 73221
    Prev
    Next
    INDEX
    Explanations

    TV series, shows, genres

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

    The neuron fires on key thematic or genre words—especially nouns naming a show’s subject matter (e.g. “music,” “medical,” “crime,” “NASCAR,” “rock,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     you
    -1.27
     without
    -1.16
     städ
    -1.10
     our
    -1.09
     or
    -0.98
    ロ
    -0.98
    ⅙
    -0.98
    лә
    -0.97
    ……
    -0.96
     liebt
    -0.96
    POSITIVE LOGITS
     plages
    1.16
     why
    1.16
    那里
    1.13
    Neden
    1.12
     тамо
    1.12
     mengenakan
    1.11
    欸
    1.11
    izou
    1.11
     doméstica
    1.11
    hoenix
    1.09
    Activations Density 0.227%

    No Known Activations