© 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. 102543
    Prev
    Next
    INDEX
    Explanations

    foreign languages and characters

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

    The neuron fires on numeric literals (numbers) in the text.

    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
     because
    -1.45
     pensamento
    -1.37
     although
    -1.34
    ꒳
    -1.31
     chapéu
    -1.31
     by
    -1.31
     mourut
    -1.28
    <bos>
    -1.25
     not
    -1.23
    空港
    -1.23
    POSITIVE LOGITS
     Franse
    1.54
    their
    1.49
    鸲
    1.48
    vät
    1.46
     ihre
    1.45
     bliver
    1.44
     halv
    1.42
     få
    1.41
     cirka
    1.41
     yore
    1.40
    Activations Density 0.015%

    No Known Activations