© 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. 26552
    Prev
    Next
    INDEX
    Explanations

    questions and statements

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

    The neuron fires on strongly negative or emphatic language—insults, negations, all-caps words, question marks, exclamation points, and other markers of intense sentiment.

    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
    🤐
    -1.00
     tiež
    -0.99
     therefore
    -0.97
     וכן
    -0.94
    😶
    -0.93
     verranno
    -0.93
     newOwner
    -0.92
     niektor
    -0.90
     sih
    -0.90
    ará
    -0.89
    POSITIVE LOGITS
    明明
    1.24
     vừa
    1.16
     I
    0.99
    人都
    0.94
    居然
    0.91
    even
    0.90
     how
    0.90
    もしっかり
    0.87
     why
    0.86
     TextEditing
    0.86
    Activations Density 0.058%

    No Known Activations