© 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. 10-GEMMASCOPE-RES-131K
    7. 44788
    Prev
    Next
    INDEX
    Explanations

    foreign languages and code

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

    The neuron activates on tokens from non-English text (i.e. when the passage switches into other languages).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    -2.67
     funcionam
    -2.48
     \
    -2.44
    に関しては
    -2.44
    ѻ
    -2.42
     Firstly
    -2.33
     generalmente
    -2.31
    ed
    -2.31
     Allowing
    -2.30
     Here
    -2.28
    POSITIVE LOGITS
    $
    3.34
    ࿆
    3.23
    逦
    3.14
    )　
    3.06
     グリル
    2.66
    ྜ
    2.64
     Oeste
    2.47
    )：
    2.47
    just
    2.45
    )-
    2.45
    Activations Density 0.003%

    No Known Activations