© 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. 73204
    Prev
    Next
    INDEX
    Explanations

    years and numbers

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

    The neuron is picking up on numeric tokens (years, dates, statistics, and other digit sequences).

    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
     etwa
    -1.41
    　　“
    -1.27
    不少
    -1.25
    </strong>
    -1.25
     novedades
    -1.24
    Meanwhile
    -1.23
    हर
    -1.20
    Nowadays
    -1.20
    uju
    -1.18
    𝑳
    -1.17
    POSITIVE LOGITS
    ไลน์
    1.23
    😤
    1.20
     also
    1.20
     می‌باشد
    1.16
     will
    1.16
     was
    1.13
    🤫
    1.13
    🤪
    1.13
    женские
    1.12
    🥴
    1.12
    Activations Density 0.049%

    No Known Activations