© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 119488
    Prev
    Next
    INDEX
    Explanations

    selection or choice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    6
    0.47
    5
    0.47
    9
    0.43
    iges
    0.43
    8
    0.42
    7
    0.42
    æs
    0.41
    umes
    0.41
    Below
    0.40
    0
    0.40
    POSITIVE LOGITS
     выбран
    0.60
     destination
    0.51
     chosen
    0.50
     পরবর্তী
    0.48
     target
    0.47
     выбрали
    0.47
     മറ്റൊരു
    0.47
     substituent
    0.45
    特定の
    0.45
     subsequent
    0.44
    Activations Density 0.000%

    No Known Activations