© 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. 32209
    Prev
    Next
    INDEX
    Explanations

    except followed by conditions

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

    The neuron fires on occurrences of exception markers—especially the word “Except” (often in “Except for…” clauses).

    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
     både
    -1.66
     other
    -1.49
     autres
    -1.47
     altres
    -1.44
     autre
    -1.44
     même
    -1.44
     גם
    -1.44
     both
    -1.31
     также
    -1.25
     arī
    -1.24
    POSITIVE LOGITS
     maybe
    2.39
     vielleicht
    2.33
     perhaps
    2.27
     misschien
    2.25
    Perhaps
    2.25
     for
    2.14
    Maybe
    2.09
     quizás
    2.05
     when
    2.02
     Perhaps
    2.02
    Activations Density 0.042%

    No Known Activations