© 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. 34615
    Prev
    Next
    INDEX
    Explanations

    " followed by common words

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

    This neuron detects the beginnings of direct quotations, firing strongly on opening quotation marks and the first words inside quoted speech.

    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
     también
    -1.11
    Также
    -1.10
    También
    -1.01
    anzeigen
    -1.00
    なども
    -1.00
     aforementioned
    -0.99
    isClosed
    -0.99
    などを
    -0.98
     городской
    -0.97
     também
    -0.96
    POSITIVE LOGITS
     we
    1.96
     our
    1.18
     it
    1.16
     will
    1.15
     this
    1.09
    ۡ
    1.05
     [
    1.02
    屿
    1.01
     regret
    1.01
     ランキング
    0.97
    Activations Density 0.025%

    No Known Activations