© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 904
    Prev
    Next
    INDEX
    Explanations

    importance of context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ด
    1.84
    й
    1.75
    ก
    1.75
    ب
    1.70
    क
    1.64
    ã
    1.61
    <0xF2>
    1.57
    D
    1.56
    ल
    1.54
    ди
    1.50
    POSITIVE LOGITS
    闼
    1.37
    <0x80>
    1.34
    ことにより
    1.33
     pamoja
    1.32
    ेस
    1.27
    ون
    1.26
    1.25
    ра
    1.24
    ून
    1.23
    ementara
    1.22
    Activations Density 0.006%

    No Known Activations