© 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. 104392
    Prev
    Next
    INDEX
    Explanations

    sentence ending punctuation

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

    The neuron fires on standalone numeric tokens (e.g. vote counts, view counts, scores).

    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
    ですが
    -1.19
     поэтому
    -1.16
    がありますが
    -0.96
    が
    -0.95
    長野
    -0.95
    は
    -0.94
     derr
    -0.94
     때문에
    -0.94
     поскольку
    -0.94
    なんか
    -0.94
    POSITIVE LOGITS
    ?
    1.88
     or
    1.34
    ícias
    1.17
     incríveis
    1.17
    ofing
    1.16
    ǀ
    1.13
     sintió
    1.12
    Lets
    1.09
     powiedział
    1.08
    ました
    1.07
    Activations Density 0.045%

    No Known Activations