© 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. 106980
    Prev
    Next
    INDEX
    Explanations

    types of media productions

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

    The neuron responds to numeric tokens and quantifications (numbers, dates, counts, and other numerical expressions).

    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
     atoi
    -0.82
    ńska
    -0.79
     Récup
    -0.78
     Créer
    -0.77
     الناس
    -0.77
    ńskie
    -0.77
    ────
    -0.76
    verständ
    -0.75
    ]=>
    -0.75
    观众
    -0.75
    POSITIVE LOGITS
     commercials
    2.17
     films
    2.09
     movies
    2.06
     TV
    2.03
     television
    1.99
     film
    1.97
     movie
    1.76
     tv
    1.68
     projects
    1.60
     advertisements
    1.56
    Activations Density 0.069%

    No Known Activations