© 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. 73090
    Prev
    Next
    INDEX
    Explanations

    past or present state of time

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

    This neuron detects numeric tokens (e.g., numbers and measurements) 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
     latar
    -1.30
    👆
    -1.16
     simbol
    -1.14
    𝒪
    -1.12
    🏿
    -1.12
    signia
    -1.11
     Aarhus
    -1.10
     こちら
    -1.09
    🐷
    -1.09
    itiert
    -1.09
    POSITIVE LOGITS
     więc
    1.19
     فقط
    1.18
     a
    1.14
    ן
    1.05
    商城
    1.04
     takich
    1.03
    '
    1.02
     graced
    1.01
     cheio
    1.01
     about
    1.01
    Activations Density 0.021%

    No Known Activations