© 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. 91401
    Prev
    Next
    INDEX
    Explanations

    please click links

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

    The neuron is highly sensitive to interface call-outs—especially registration or login prompts (e.g. “Not … yet?”, “Sign up,” “Forgot …?”) and related UI/action words.

    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
     watched
    -0.87
     downloaded
    -0.84
    downloaded
    -0.83
    Біо
    -0.82
    sont
    -0.82
     tion
    -0.79
    psico
    -0.79
     replacing
    -0.78
     contacting
    -0.77
     asumi
    -0.75
    POSITIVE LOGITS
     click
    4.38
    Click
    3.73
     Click
    3.59
    click
    3.45
    CLICK
    3.39
     CLICK
    3.14
    点击
    2.89
     clicking
    2.53
     clicks
    2.53
     clicked
    2.31
    Activations Density 0.092%

    No Known Activations