© 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. 34012
    Prev
    Next
    INDEX
    Explanations

    determiners, pronouns, and common starters

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

    The neuron fires on standalone numeric tokens (including integers and decimals) 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_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
     therefore
    -1.16
     so
    -1.13
     поэтому
    -1.11
     this
    -1.09
     этим
    -1.00
     inilah
    -0.98
    ᄆ
    -0.95
     thus
    -0.93
    éroport
    -0.93
     metų
    -0.93
    POSITIVE LOGITS
     The
    1.20
     Regarding
    1.13
     there
    1.03
     przede
    1.02
    注重
    1.01
    也非常
    0.99
     Empieza
    0.99
    bucks
    0.98
    Regarding
    0.96
     religiosas
    0.96
    Activations Density 0.041%

    No Known Activations