© 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. 59392
    Prev
    Next
    INDEX
    Explanations

    asking questions

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

    The neuron fires on the numbering and labeling tokens of FAQ-style question headings (e.g. “1.”, “3.”, “Where”, “?”.)

    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
    ご覧
    -1.05
    んですよ
    -0.99
    odine
    -0.96
    riebene
    -0.96
     giocatori
    -0.95
    ētu
    -0.94
    Selon
    -0.93
    であり
    -0.93
    Hãy
    -0.91
    寶寶
    -0.91
    POSITIVE LOGITS
     how
    3.44
     can
    3.16
     what
    3.03
     What
    2.19
     will
    2.17
     does
    2.14
     How
    2.13
     why
    2.08
     I
    2.08
     where
    1.98
    Activations Density 0.069%

    No Known Activations