© 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. 22-GEMMASCOPE-RES-131K
    7. 27372
    Prev
    Next
    INDEX
    Explanations

    questions about solutions

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

    This neuron detects interrogative/question content—phrasing that asks “is there a way…?”, uses question words or a trailing “?”, and generally marks question sentences.

    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
    utenants
    -0.96
    ciled
    -0.95
    yczny
    -0.94
     ausreichend
    -0.94
     noexcept
    -0.92
    tifier
    -0.92
     ProtoMessage
    -0.91
    と言われる
    -0.90
     genügend
    -0.88
     akces
    -0.88
    POSITIVE LOGITS
     there
    1.22
    There
    1.16
     methods
    1.09
     solutions
    1.08
     существует
    1.05
     ways
    1.02
     elér
    1.01
     gibt
    1.00
     like
    0.98
     preferably
    0.97
    Activations Density 1.036%

    No Known Activations