© 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. 40288
    Prev
    Next
    INDEX
    Explanations

    namespaces and paths

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

    The neuron activates on numeric version or schema‐identifier tokens (e.g. digits in XML/HTML/DTD headers and namespace URIs).

    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
     or
    -1.41
    Anmerkungen
    -1.30
    ambul
    -1.24
    ⿻
    -1.22
     from
    -1.20
    或是
    -1.19
     has
    -1.14
     escondido
    -1.13
    ždy
    -1.10
     found
    -1.09
    POSITIVE LOGITS
    もありました
    1.66
    もあって
    1.55
    がありますが
    1.43
    もあり
    1.41
    があり
    1.39
    ʹ
    1.30
    もあった
    1.30
     meistens
    1.28
     aceptas
    1.27
    もあるので
    1.27
    Activations Density 0.001%

    No Known Activations