© 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. 22-GEMMASCOPE-RES-131K
    7. 128195
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on words in article headlines or titles.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    future possibility or conditional

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ってしまった
    -1.02
     två
    -1.02
     Condado
    -1.02
    Long
    -1.00
     funciona
    -0.99
    on
    -0.96
    Try
    -0.96
    ≲
    -0.95
     fått
    -0.95
    ूरत
    -0.95
    POSITIVE LOGITS
     would
    1.74
     if
    1.50
     если
    1.35
     someday
    1.25
     next
    1.18
    如果
    1.13
     or
    1.13
     possible
    1.12
    だったら
    1.11
     hypothetical
    1.06
    Activations Density 0.047%

    No Known Activations