© 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. 13970
    Prev
    Next
    INDEX
    Explanations

    place names in India and Europe

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

    The neuron activates on numeric tokens, i.e. any piece of text containing digits.

    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
     the
    -1.52
    為に
    -1.41
     avrebbe
    -1.28
    おそ
    -1.27
     sarà
    -1.20
     will
    -1.17
     ざ
    -1.13
     a
    -1.13
    BaseActivity
    -1.13
    にします
    -1.11
    POSITIVE LOGITS
    quelize
    1.41
    lihatan
    1.40
    OOTDTY
    1.38
    礎
    1.38
    StoryboardSegue
    1.37
     вашего
    1.36
     déroule
    1.34
    があります
    1.34
     cojín
    1.34
     decoracion
    1.33
    Activations Density 0.037%

    No Known Activations