© 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. 91484
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by another word

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

    The neuron responds strongly to named entities and numeric/date tokens—i.e. it marks proper names, key dates, ordinals, and figures in the text.

    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
     derfor
    -1.34
     поэтому
    -1.28
     powodu
    -1.16
     jaką
    -1.15
     første
    -1.14
     сейчас
    -1.13
     daher
    -1.13
    因此
    -1.13
     ingenieros
    -1.11
     initially
    -1.10
    POSITIVE LOGITS
     other
    3.92
     elsewhere
    2.88
     another
    2.69
     similarly
    2.63
     Similarly
    2.61
     others
    2.58
    Other
    2.56
    Similarly
    2.56
     Other
    2.52
    其他
    2.44
    Activations Density 0.032%

    No Known Activations