© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8120
    Prev
    Next
    INDEX
    Explanations

    dates and years

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

    The neuron detects numeric tokens—especially years, dates, reference numbers, and other standalone numerals.

    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
    either
    -1.58
    previously
    -1.53
    ּוֹ
    -1.47
     abbildung
    -1.44
    attended
    -1.41
    CONCLUSIONES
    -1.41
    outlined
    -1.38
    Either
    -1.35
    astify
    -1.34
     magnétique
    -1.32
    POSITIVE LOGITS
     with
    1.55
     before
    1.35
     used
    1.27
     all
    1.26
     them
    1.23
     first
    1.21
     where
    1.20
     mė
    1.19
     Usually
    1.19
     eerst
    1.18
    Activations Density 0.302%

    No Known Activations