© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70819
    Prev
    Next
    INDEX
    Explanations

    catching exceptions or asking questions

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

    The neuron sharply responds to opening-parenthesis tokens (i.e. “(”).

    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
    fø
    -1.04
     cauſe
    -1.02
    eschön
    -1.01
    ᚑ
    -1.01
     poë
    -1.01
    tengo
    -1.00
    ⅴ
    -0.98
    vlo
    -0.98
     vakantie
    -0.97
     prachtige
    -0.96
    POSITIVE LOGITS
     of
    1.43
     or
    1.30
     all
    1.20
     (
    1.12
     not
    1.09
     more
    1.00
     Z
    0.93
     via
    0.91
     any
    0.91
     obtain
    0.89
    Activations Density 0.000%

    No Known Activations