© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129696
    Prev
    Next
    INDEX
    Explanations

    movie plot character roles

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

    This neuron detects when the text shifts into a film’s plot synopsis—spotting words like “plot” or “storyline” and the ensuing summary details.

    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
     atau
    -1.40
     budeme
    -1.39
     it
    -1.39
     przechowy
    -1.36
     our
    -1.30
     тази
    -1.30
    maglia
    -1.28
    äischen
    -1.28
     or
    -1.27
     nuestro
    -1.26
    POSITIVE LOGITS
     herbes
    1.41
     inz
    1.27
     alho
    1.26
     herbe
    1.25
     verdo
    1.23
     chers
    1.22
     parfums
    1.22
     hek
    1.20
     applau
    1.20
     a
    1.20
    Activations Density 0.240%

    No Known Activations