© 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. 107658
    Prev
    Next
    INDEX
    Explanations

    musical films and productions

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

    The neuron detects the canonical Wikipedia film‐article opening phrase “<Title> is a <year> <nationality> <genre> film.”

    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
    してきました
    -0.71
    Embry
    -0.71
    findall
    -0.70
    遊び
    -0.68
     develop
    -0.68
     betont
    -0.68
    恚
    -0.67
     whistles
    -0.67
     isotopes
    -0.65
     sitcom
    -0.65
    POSITIVE LOGITS
     musical
    1.63
     musicals
    1.51
    Musical
    1.38
     Musical
    1.34
     musicales
    1.33
    musical
    1.33
     music
    1.17
     singing
    1.15
     MUSICAL
    1.14
     SING
    1.13
    Activations Density 0.028%

    No Known Activations