© 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. 86339
    Prev
    Next
    INDEX
    Explanations

    acceptance or acceptance of

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

    The neuron activates on various forms of the root “accept,” i.e. tokens like accept, accepted, acceptance, etc.

    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
     \
    -2.08
     $
    -2.06
    ar
    -2.00
      
    -1.97
    </strong>
    -1.88
    之上
    -1.88
    塌
    -1.84
    眼光
    -1.82
    ですので
    -1.80
     oczywiście
    -1.76
    POSITIVE LOGITS
    鏨
    2.02
    ского
    1.84
    鏵
    1.76
    頽
    1.74
    We
    1.73
     utveckling
    1.70
    ﹶ
    1.68
    With
    1.68
    缦
    1.67
    Many
    1.66
    Activations Density 0.043%

    No Known Activations