© 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. 34-GEMMASCOPE-RES-131K
    7. 108583
    Prev
    Next
    INDEX
    Explanations

    dismissing alerts or controllers

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

    The neuron fires on tokens containing the string “dismiss” (e.g. dismiss, dismissible, 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_34/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
     الرغم
    -0.94
    enuto
    -0.90
    avaş
    -0.86
     Vera
    -0.84
    ombia
    -0.81
    uros
    -0.79
    isUser
    -0.78
    waffe
    -0.77
    '}';
    -0.75
    ΡΙ
    -0.75
    POSITIVE LOGITS
    新規
    0.86
     this
    0.86
    भव
    0.78
     dismiss
    0.75
     regener
    0.75
    tify
    0.73
    県の
    0.73
     Keystone
    0.73
    ｌ
    0.72
    dismiss
    0.71
    Activations Density 0.003%

    No Known Activations