Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 659
    Prev
    Next
    INDEX
    Explanations

    URLs and possessives

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

    This neuron detects programming/code content—tokens from code snippets (variable/function names, array identifiers, numeric literals and other code-related tokens).

    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_31_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
     книге
    0.21
     酸
    0.20
    เชสเตอร์
    0.20
     бух
    0.19
    Agriculture
    0.19
    itochond
    0.18
    CHEMY
    0.18
     книга
    0.18
    คองโก
    0.18
    谴
    0.18
    POSITIVE LOGITS
     even
    0.22
     much
    0.22
     same
    0.22
     only
    0.21
     doesn
    0.21
     so
    0.21
     use
    0.20
     It
    0.20
     wasn
    0.20
     other
    0.19
    Activations Density 4.132%

    No Known Activations