© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1527
    Prev
    Next
    INDEX
    Explanations

    finds and highlights quantitative data and structured numerical blocks within a document.

    oai_token-act-pair · gpt-5-nanoTriggered by @nvasa7707
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_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
     τη
    0.72
    戎
    0.63
     CPF
    0.63
     στη
    0.62
     LEP
    0.62
    ޞ
    0.62
     ло
    0.61
     திமுக
    0.61
     선물
    0.61
    ಿಗಳ
    0.60
    POSITIVE LOGITS
    のア
    1.94
     ア
    1.91
     А
    1.84
    ア
    1.76
     아
    1.73
    А
    1.67
     AD
    1.63
    阿
    1.61
     Á
    1.59
     অ্যা
    1.58
    Activations Density 2.261%

    No Known Activations