© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 98358
    Prev
    Next
    INDEX
    Explanations

    credits and cast members

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

    The neuron fires on film‐ or media‐credit lines—mentions of who directed, wrote, produced, or otherwise worked on a movie (i.e. names plus their production roles).

    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
     when
    -1.13
     either
    -0.99
    жности
    -0.90
    にします
    -0.90
     ]);
    -0.90
    Faça
    -0.89
    Tutto
    -0.89
    ülen
    -0.87
     where
    -0.87
    Usuarios
    -0.86
    POSITIVE LOGITS
     who
    1.16
     whom
    1.13
    abaikan
    1.05
    さも
    1.02
     assistant
    1.02
    vábbi
    1.00
    ('|
    0.99
    撺
    0.98
     supported
    0.98
     fatale
    0.96
    Activations Density 0.090%

    No Known Activations