© 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. 6112
    Prev
    Next
    INDEX
    Explanations

    logs that

    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
    named
    0.52
    end
    0.44
     recreated
    0.43
    ко
    0.42
    appearing
    0.41
    مي
    0.41
    packaged
    0.41
    W
    0.41
    𝙙
    0.39
    Named
    0.39
    POSITIVE LOGITS
    ตัน
    0.55
    alir
    0.53
     anal
    0.50
     konfigur
    0.49
    метка
    0.49
     »,
    0.49
    ']),
    0.48
     타고
    0.48
     determin
    0.48
     kesel
    0.48
    Activations Density 0.000%

    No Known Activations