© 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. 16146
    Prev
    Next
    INDEX
    Explanations

    for all

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

    The neuron is keyed to spotting logical‐quantifier words and phrases (e.g. “any,” “exists,” “forall”) in formal mathematical definitions.

    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
     until
    -1.21
     will
    -1.04
    Já
    -0.98
    brenner
    -0.96
     while
    -0.95
     since
    -0.94
    republik
    -0.90
     these
    -0.88
    xffffff
    -0.87
    criptors
    -0.85
    POSITIVE LOGITS
    कि
    0.96
    FlatButton
    0.94
     PATIENT
    0.87
    哪裡
    0.86
     préférence
    0.84
    ksk
    0.84
    みんな
    0.84
     bardziej
    0.83
    ifte
    0.82
     hábitat
    0.82
    Activations Density 0.058%

    No Known Activations