© 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. 34-GEMMASCOPE-RES-131K
    7. 76355
    Prev
    Next
    INDEX
    Explanations

    Overland campaigns

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

    The neuron strongly activates on proper nouns that denote geographic locations (e.g., states, counties, towns, battle names).

    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
     respuestas
    -0.79
     instancia
    -0.77
     presque
    -0.77
    axa
    -0.75
     אר
    -0.71
     znan
    -0.71
     cả
    -0.71
     clé
    -0.69
     ruido
    -0.69
     gefunden
    -0.69
    POSITIVE LOGITS
     Petersburg
    0.84
    seurs
    0.73
    Année
    0.69
     Mekong
    0.69
     tann
    0.66
    Spinner
    0.66
    クタイ
    0.66
    蜢
    0.66
    SHARE
    0.66
     Prince
    0.65
    Activations Density 0.018%

    No Known Activations