© 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. 34-GEMMASCOPE-RES-131K
    7. 119156
    Prev
    Next
    INDEX
    Explanations

    DREAM Act rally join

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

    The neuron activates strongly on emphatic, exclamatory language—especially words and punctuation in sentences bursting with exclamation points.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     FUCKING
    -1.32
    Fuck
    -1.23
    Fucking
    -1.13
     Fucking
    -1.13
     Fuck
    -1.13
     fucking
    -1.11
     SHIT
    -1.10
     fuckin
    -1.09
    fucking
    -1.09
    fuck
    -1.04
    POSITIVE LOGITS
     считается
    1.08
     girls
    1.07
     allergic
    1.03
    🔳
    1.02
     nonstop
    1.00
    丹药
    1.00
    祕
    0.97
     rapidez
    0.97
    nonzero
    0.97
     officially
    0.96
    Activations Density 0.012%

    No Known Activations