© 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. 8670
    Prev
    Next
    INDEX
    Explanations

    excluding exceptions elimination exclusivity

    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
    <0x80>
    2.14
    ﻪ
    1.96
    ，
    1.89
    即使
    1.84
    可以
    1.80
    จะ
    1.77
    不及
    1.73
    溂
    1.72
     oluşan
    1.71
    及
    1.71
    POSITIVE LOGITS
    ר
    1.91
    ことになる
    1.91
    ва
    1.88
    ра
    1.86
    IN
    1.80
    lN
    1.80
    ively
    1.78
    т
    1.72
    ς
    1.68
    ן
    1.64
    Activations Density 0.311%

    No Known Activations