© 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. 44433
    Prev
    Next
    INDEX
    Explanations

    import Krist Plot

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

    The neuron fires on numeric tokens (including integers and decimals), i.e. any occurrence of a number or quantity.

    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
     españolas
    -1.74
     deportivas
    -1.63
    桖
    -1.59
     this
    -1.55
     醬
    -1.52
    τής
    -1.51
     aéreas
    -1.50
     any
    -1.49
    чити
    -1.48
    اعمال
    -1.47
    POSITIVE LOGITS
    a
    1.84
    g
    1.77
    h
    1.76
    u
    1.59
     They
    1.56
    r
    1.53
    t
    1.49
    1.49
    e
    1.43
    os
    1.40
    Activations Density 0.004%
    No Known Activations