© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79580
    Prev
    Next
    INDEX
    Explanations

    questions about personal thoughts

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

    The neuron flags question-related tokens—e.g. question marks and words introducing or framing questions.

    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
    ixante
    -1.09
    taya
    -1.07
    顫
    -1.04
    Markets
    -1.02
     minden
    -1.02
     SCHOOLS
    -1.01
     prim
    -1.01
     Дмитрий
    -1.00
    simply
    -0.99
     simplesmente
    -0.98
    POSITIVE LOGITS
     about
    1.66
     different
    1.45
     think
    1.29
     now
    1.27
     knows
    1.27
     know
    1.22
     teď
    1.20
     χρησιμοποι
    1.16
    When
    1.14
     remember
    1.13
    Activations Density 0.007%

    No Known Activations