© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60370
    Prev
    Next
    INDEX
    Explanations

    conditions criteria

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

    The neuron consistently activates on occurrences of the word “criteria.”

    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
     émission
    -3.20
     évaluation
    -2.77
     icône
    -2.75
     activité
    -2.67
     évolution
    -2.52
    derdag
    -2.52
    獪
    -2.50
    ꜆
    -2.48
     ouverture
    -2.39
    dámské
    -2.39
    POSITIVE LOGITS
    .
    3.50
    e
    2.47
    之为
    2.47
    .”
    2.41
     dibujado
    2.34
    所说的
    2.28
    是你
    2.27
    '
    2.25
     sonriendo
    2.25
     techniczne
    2.20
    Activations Density 0.005%

    No Known Activations