© 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. 112716
    Prev
    Next
    INDEX
    Explanations

    contractions and possessives

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

    The neuron fires most strongly on numeric or quantitative expressions (digits, years, percentages, and similar number tokens).

    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
     from
    -1.74
     schreef
    -1.69
    isesta
    -1.65
    Posté
    -1.59
    Besos
    -1.50
    Več
    -1.43
    עיף
    -1.42
     пароль
    -1.41
    unggah
    -1.41
     Belakang
    -1.41
    POSITIVE LOGITS
     it
    1.76
     robić
    1.72
     zrobić
    1.67
    ↵
    1.52
    它
    1.40
     anything
    1.35
     
    1.33
    _
    1.32
     nothing
    1.31
     一
    1.31
    Activations Density 0.103%

    No Known Activations