© 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. 113243
    Prev
    Next
    INDEX
    Explanations

    external", "Category", "References", "Bibliography"

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

    This neuron does not activate on any tokens in these examples.

    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
    ichtete
    -1.52
     konz
    -1.47
    UseVisualStyle
    -1.45
     Viitattu
    -1.44
     kompati
    -1.41
     Majority
    -1.41
    谂
    -1.41
    了不少
    -1.40
    bigniew
    -1.40
    艿
    -1.39
    POSITIVE LOGITS
     verwendeten
    1.69
     immagine
    1.64
    4
    1.60
    3
    1.43
    colates
    1.43
     soste
    1.41
     are
    1.40
    は
    1.38
     sufficiente
    1.37
    はその
    1.35
    Activations Density 0.006%

    No Known Activations