© 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. 39988
    Prev
    Next
    INDEX
    Explanations

    captcha or start of words

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

    The neuron detects mentions of “captcha” (including variants like “reCaptcha,” “CAPTCHA,” etc.) in the text.

    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
     was
    -2.06
    翾
    -2.05
    </em>
    -1.98
    ‘
    -1.93
     But
    -1.86
     \&
    -1.84
    玬
    -1.84
     –
    -1.78
    ↵↵
    -1.76
    ited
    -1.76
    POSITIVE LOGITS
    iſter
    2.27
    imantan
    2.20
     cambian
    2.05
    鏷
    2.02
    cimiento
    1.99
    enfone
    1.93
     BOTH
    1.91
     любой
    1.91
    section
    1.89
     sufren
    1.88
    Activations Density 0.001%

    No Known Activations