© 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. 22-GEMMASCOPE-RES-131K
    7. 15198
    Prev
    Next
    INDEX
    Explanations

    movie titles

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

    The neuron fires on capitalized content words that are parts of movie titles or film names.

    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
     also
    -1.84
     santuario
    -1.65
     genio
    -1.59
     nace
    -1.56
     castelo
    -1.54
     condominio
    -1.53
     invito
    -1.52
     testamento
    -1.52
     who
    -1.49
     calavera
    -1.48
    POSITIVE LOGITS
    فران
    1.54
    Materiál
    1.52
     despertar
    1.51
     interessanti
    1.47
    رياض
    1.46
     Since
    1.45
     ложка
    1.45
    Geograf
    1.43
     particolarmente
    1.42
     consideró
    1.42
    Activations Density 0.050%

    No Known Activations