© 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. 22-GEMMASCOPE-RES-131K
    7. 14870
    Prev
    Next
    INDEX
    Explanations

    place names followed by location type

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

    The neuron selectively activates on tokens that are components of named places (proper nouns in geographic or institutional 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_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
    なるべく
    -1.53
    昔の
    -1.52
    凄く
    -1.50
    為に
    -1.44
    一つの
    -1.44
    开玩笑
    -1.43
    たまたま
    -1.42
    できるだけ
    -1.41
    色々な
    -1.39
    色んな
    -1.38
    POSITIVE LOGITS
     at
    1.49
     accesorios
    1.42
     in
    1.39
     Accesorios
    1.34
     guantes
    1.30
    Millan
    1.29
     cojín
    1.29
     MessageBoxIcon
    1.27
    海道
    1.26
     of
    1.24
    Activations Density 0.053%

    No Known Activations