© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28068
    Prev
    Next
    INDEX
    Explanations

    types of creative works

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

    The neuron fires on words naming media or creative‐work types or their descriptors (e.g. “piece,” “film,” “documentary,” “tale,” “adventure,” “comedy”).

    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
     such
    -1.56
     therefore
    -1.27
     then
    -1.21
     since
    -1.19
    although
    -1.18
     their
    -1.17
     instead
    -1.17
     like
    -1.16
    and
    -1.16
     hence
    -1.16
    POSITIVE LOGITS
     that
    1.72
     enthou
    1.23
     koja
    1.20
     humeur
    1.17
     vernis
    1.15
     consé
    1.13
    ที่มี
    1.12
     blessure
    1.11
     maquillage
    1.10
    Ār
    1.10
    Activations Density 0.035%

    No Known Activations