© 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. 33196
    Prev
    Next
    INDEX
    Explanations

    used to describe a state of completeness or excellence

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

    The neuron strongly activates on the exact adjective “perfect” (in any context).

    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
    ↵↵
    -2.91
    ೣ
    -2.67
     focuses
    -2.53
    僦
    -2.53
    粁
    -2.52
     dando
    -2.50
    ৢ
    -2.50
     terrific
    -2.50
    ឵
    -2.48
     delightfully
    -2.45
    POSITIVE LOGITS
    Although
    4.03
    While
    3.97
    Despite
    3.81
    Even
    3.66
    Almost
    3.64
    Some
    3.59
    Though
    3.47
    Surprisingly
    3.44
    Because
    3.44
    With
    3.42
    Activations Density 0.011%

    No Known Activations