© 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. 41-GEMMASCOPE-2-RES-65K
    7. 1129
    Prev
    Next
    INDEX
    Explanations

    recognizes/understands

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_65k_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
    此外
    0.55
    whom
    0.50
    ਦ
    0.49
     যিনি
    0.48
    ただし
    0.48
    Кто
    0.48
     በላይ
    0.47
    Gaussian
    0.46
    Causes
    0.46
    ٽ
    0.46
    POSITIVE LOGITS
     recognizes
    0.83
    ’
    0.78
    '
    0.77
     itself
    0.75
     officials
    0.74
     expects
    0.74
     encourages
    0.73
     employs
    0.73
     considers
    0.73
     understands
    0.73
    Activations Density 0.263%

    No Known Activations