© 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. 903
    Prev
    Next
    INDEX
    Explanations

    instructions and information related to plugin development for language models.

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

    pronouns and people

    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
    5
    0.33
    +
    0.30
    3
    0.29
    高
    0.29
    ですが
    0.28
     dessen
    0.28
    값
    0.28
    2
    0.28
    6
    0.28
    ৫
    0.27
    POSITIVE LOGITS
     you
    0.60
     they
    0.59
     it
    0.57
     people
    0.55
     we
    0.53
     તેઓ
    0.52
     люди
    0.48
    我們
    0.47
     लोगों
    0.47
     bạn
    0.47
    Activations Density 1.426%

    No Known Activations