© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26472
    Prev
    Next
    INDEX
    Explanations

    places and activities

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

    The neuron is sensitive to tokens containing non-ASCII characters—especially letters with diacritics.

    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
    P
    -1.17
    つづく
    -1.13
    S
    -1.12
    -1.08
    []
    -1.07
    L
    -1.05
    [
    -1.04
     it
    -1.02
     So
    -1.00
    A
    -1.00
    POSITIVE LOGITS
     manzanas
    1.27
    놋
    1.16
     herencia
    1.09
    ㈯
    1.08
    があるので
    1.07
     interfaz
    1.05
    ⸫
    1.04
    乙女
    1.03
    
    1.03
    tronlink
    1.02
    Activations Density 0.012%
    No Known Activations