© 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. 67378
    Prev
    Next
    INDEX
    Explanations

    live action / short films / phage

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

    the phrase "live-action" in media descriptions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron strongly detects the phrase “live-action” (i.e. occurrences of “live-action” describing film or video content).

    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
    providedIn
    -1.65
     nhưng
    -1.53
    autorelease
    -1.50
    却又
    -1.49
     regained
    -1.45
     booming
    -1.42
     provare
    -1.41
     неё
    -1.39
     gü
    -1.38
     beli
    -1.38
    POSITIVE LOGITS
    𓋼
    1.63
    {
    1.62
    で
    1.51
     также
    1.37
    Ꮉ
    1.34
    那天
    1.33
    ração
    1.32
    𓆜
    1.30
    δος
    1.30
    なかなか
    1.30
    Activations Density 0.045%

    No Known Activations