© 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. 104263
    Prev
    Next
    INDEX
    Explanations

    states and cities

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

    The neuron strongly activates on title-cased or proper-noun tokens (e.g. names of places, organizations, headlines).

    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
     condominio
    -1.00
     vasca
    -0.94
     custodia
    -0.93
     сформи
    -0.93
     {},
    -0.91
     [],
    -0.90
     confes
    -0.90
     testamento
    -0.89
    分けて
    -0.88
     successo
    -0.88
    POSITIVE LOGITS
     its
    1.59
    Its
    1.09
    してます
    1.06
    хъ
    1.04
     vuelva
    1.02
    其
    1.00
    PathParam
    1.00
     Its
    0.96
    āci
    0.96
    тров
    0.95
    Activations Density 0.110%

    No Known Activations