© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 245135
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily detects numeric tokens and numeric/legal citation-like sequences (i.e., numbers and number-heavy references).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝗇
    0.43
     필요
    0.41
     ontwikkelen
    0.40
     irány
    0.40
     ಸಾಧ್ಯ
    0.38
    椛
    0.38
    experiment
    0.38
     кө
    0.38
    ◐
    0.37
    akkan
    0.37
    POSITIVE LOGITS
     reservados
    0.39
     čo
    0.38
     dopo
    0.37
    After
    0.37
     Dados
    0.37
     unix
    0.37
     After
    0.35
    Dopo
    0.35
     después
    0.35
     Cozy
    0.35
    Activations Density 0.000%

    No Known Activations