© 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. 74012
    Prev
    Next
    INDEX
    Explanations

    consistency or consistency

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

    The neuron is tuned to detect occurrences of the word “consistent” (and its variant “consistency”).

    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
     magnificent
    -3.13
     delightfully
    -2.84
     quintessential
    -2.80
     deliciously
    -2.78
     superb
    -2.78
     .......
    -2.77
     таких
    -2.75
     serene
    -2.73
    actéristi
    -2.70
     captivating
    -2.69
    POSITIVE LOGITS
    '
    2.78
    when
    2.77
    ！(
    2.59
     informar
    2.50
    𓍯
    2.47
    \
    2.38
    ”，
    2.30
    浥
    2.23
    Even
    2.22
     beslu
    2.19
    Activations Density 0.009%

    No Known Activations