© 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. 8050
    Prev
    Next
    INDEX
    Explanations

    contains information or examples

    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
    ಲ
    2.09
     whore
    1.92
    ب
    1.88
    지
    1.83
    ਾ
    1.82
    적인
    1.81
    ้อง
    1.79
    ਲ
    1.78
    ERE
    1.75
    কে
    1.67
    POSITIVE LOGITS
    り
    2.59
    tedir
    2.25
     multitudes
    2.16
     đựng
    2.09
    滉
    2.06
    piece
    2.05
    polymer
    2.05
    daki
    2.03
     enthalten
    2.03
    หนด
    2.02
    Activations Density 0.038%

    No Known Activations