© 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. 9519
    Prev
    Next
    INDEX
    Explanations

    #!/usr/bin/env bin

    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
     Circles
    0.44
    ړه
    0.43
    circles
    0.41
    浼
    0.40
    വേ
    0.39
    ంశ
    0.39
     Pest
    0.38
     redor
    0.38
     Braun
    0.37
    荨
    0.37
    POSITIVE LOGITS
    bin
    0.88
     bin
    0.85
    sbin
    0.69
    BIN
    0.62
    Bin
    0.61
     binoculars
    0.60
     bins
    0.57
     Bin
    0.55
     telescope
    0.50
     BIN
    0.50
    Activations Density 0.003%

    No Known Activations