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-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 1021
    Prev
    Next
    INDEX
    Explanations

    structured list segments and metric annotations, such as section headers with colons and quantitative ranges with units (percentages, time, money, per-month).

    oai_token-act-pair · gpt-5Triggered by @irajjmoradi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     पैसे
    1.11
    țiuni
    1.03
    ബർ
    1.02
    <unused2118>
    1.01
    鸴
    1.01
     આ
    0.99
    椷
    0.98
    鿆
    0.98
    ட்
    0.98
    醿
    0.97
    POSITIVE LOGITS
     again
    1.30
    こちらも
    1.04
    again
    0.99
     Again
    0.91
    Again
    0.84
     igen
    0.79
    同樣
    0.73
     novamente
    0.72
     nuevamente
    0.72
    と同様
    0.71
    Activations Density 3.481%

    No Known Activations