© 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. 31-GEMMASCOPE-2-RES-65K
    7. 17111
    Prev
    Next
    INDEX
    Explanations

    technical specifications and instructions for computer components.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    first / initial

    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_31_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
    ান্তে
    0.44
     എന്ന്
    0.43
    っても
    0.42
    Eddie
    0.42
    uatu
    0.42
     insbesondere
    0.41
    Patrick
    0.39
    翌
    0.38
    Especially
    0.38
    とも
    0.38
    POSITIVE LOGITS
     первом
    0.88
     पहला
    0.88
     pertama
    0.87
    第一個
    0.86
     primeira
    0.82
     pierwszym
    0.82
     första
    0.81
     первого
    0.80
     primeiro
    0.80
     eerste
    0.80
    Activations Density 0.769%

    No Known Activations