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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 42123
    Prev
    Next
    INDEX
    Explanations

    version numbers like 7

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

    the neuron detects numeric tokens—especially version numbers and other numeric literals in technical text.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    .
    0.33
    ط
    0.33
     Inggris
    0.32
    ay
    0.30
     incroyable
    0.30
    น
    0.30
    ق
    0.29
     ingl
    0.29
    द
    0.29
     negara
    0.28
    POSITIVE LOGITS
     পরিমাণ
    0.22
     \"
    0.22
    ται
    0.21
    ఎల్
    0.21
    కోవడం
    0.21
    LookAndFeel
    0.21
    शुदा
    0.21
    MathOperator
    0.21
    emat
    0.21
     झाल
    0.21
    Activations Density 0.074%

    No Known Activations