© 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. 6598
    Prev
    Next
    INDEX
    Explanations

    Chinese and other Asian characters

    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
    戤
    1.34
     muque
    1.18
    spacePad
    1.13
    紾
    1.12
    溸
    1.11
    VILLE
    1.10
    IONAL
    1.09
     ribu
    1.09
    んにちは
    1.07
    ANDER
    1.06
    POSITIVE LOGITS
    G
    1.38
    म
    1.28
    ab
    1.27
     '
    1.27
     a
    1.25
     the
    1.23
    av
    1.21
      
    1.16
    al
    1.16
    <h2>
    1.14
    Activations Density 0.120%

    No Known Activations