© 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. 14623
    Prev
    Next
    INDEX
    Explanations

    headings, summaries, or instructions

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

    The neuron fires on numeric literals—tokens containing digits or numbers (including decimals).

    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
     those
    -1.84
     when
    -1.74
     many
    -1.60
     because
    -1.52
     frequently
    -1.43
     both
    -1.42
     three
    -1.41
     oftentimes
    -1.39
     these
    -1.38
     undeniably
    -1.38
    POSITIVE LOGITS
    }%
    1.48
    ()<<
    1.35
    isition
    1.35
    --)
    1.34
    >';
    1.23
     تخصص
    1.22
    ⎞
    1.22
    ôs
    1.20
    
    1.19
     luscious
    1.17
    Activations Density 0.001%

    No Known Activations