© 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. 22-GEMMASCOPE-RES-131K
    7. 35609
    Prev
    Next
    INDEX
    Explanations

    what next

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

    The neuron fires on aggressive, threatening, or war‐like language signaling violence or extreme confrontation.

    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
     its
    -1.29
     Bereichen
    -1.04
     or
    -1.02
    ּוֹ
    -1.01
     and
    -0.93
    香水
    -0.91
    大半
    -0.91
     że
    -0.90
     at
    -0.90
     ziemlich
    -0.90
    POSITIVE LOGITS
     addirittura
    1.13
    !
    1.05
    alingen
    1.05
     immediatamente
    1.02
    大丈夫です
    0.99
    Prijs
    0.98
    こともある
    0.97
    いいですね
    0.96
     {[
    0.96
     heretofore
    0.96
    Activations Density 0.082%

    No Known Activations