© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 2465
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on individual tokens that serve as strong numeric/contextual anchors—e.g. “push” in a betting‐spread context or “year” following a date—i.e. it flags tokens tightly coupled to numeric or date information.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ementara
    0.77
     vielfält
    0.77
     มือ
    0.74
     교수
    0.73
    ylsulfanyl
    0.72
     ktoré
    0.72
    álisis
    0.72
    ِر
    0.71
     stateMutability
    0.70
    înes
    0.70
    POSITIVE LOGITS
     Etihad
    0.82
     Oceania
    0.81
     Atletico
    0.79
     Genocide
    0.77
     genocide
    0.75
     discredit
    0.75
     नाराजगी
    0.74
     Kanye
    0.73
     Tonga
    0.73
     ceasefire
    0.71
    Activations Density 0.000%

    No Known Activations