© 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. 10-GEMMASCOPE-RES-131K
    7. 15140
    Prev
    Next
    INDEX
    Explanations

    good enough

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

    The neuron fires on occurrences of the word “enough,” especially in the phrase “good enough.”

    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
    Gön
    -1.60
     hjelp
    -1.59
     is
    -1.55
     dôle
    -1.52
    fungsi
    -1.52
    还挺
    -1.50
    滹
    -1.50
    Consejos
    -1.50
    不仅
    -1.49
     medlemmer
    -1.49
    POSITIVE LOGITS
     occasionally
    1.64
     則
    1.53
     then
    1.53
     mountains
    1.47
     haven
    1.47
    ありますか
    1.45
     mostly
    1.40
    "
    1.39
    cetamol
    1.38
     until
    1.37
    Activations Density 0.006%

    No Known Activations