© 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. 128987
    Prev
    Next
    INDEX
    Explanations

    documentary film

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

    The neuron flags mentions of documentaries (including variants like “doco,” “documentary,” “Documentaries,” etc.).

    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
     There
    -1.76
     by
    -1.48
     many
    -1.42
    ?"
    -1.39
     any
    -1.38
     disconcer
    -1.36
     erste
    -1.33
     nią
    -1.33
    
    -1.30
     encontraban
    -1.30
    POSITIVE LOGITS
     maske
    1.66
     documentaries
    1.65
     ‘
    1.64
    rive
    1.59
     aussit
    1.55
     kristal
    1.49
     medis
    1.45
     avantages
    1.44
     merke
    1.37
     borbo
    1.37
    Activations Density 0.034%

    No Known Activations