© 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. 2061
    Prev
    Next
    INDEX
    Explanations

    functional programming concepts and implementations in code snippets.

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

    commands, code, or specific terms

    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
     dajj
    0.35
     mús
    0.34
    ្រ
    0.34
    Missense
    0.34
    ﻦ
    0.34
    ोनेशिया
    0.33
    Gosudarstvennyj
    0.32
    Foods
    0.31
    좇
    0.30
    Cooldown
    0.30
    POSITIVE LOGITS
     A
    0.39
     In
    0.38
     Knowing
    0.37
     It
    0.35
     An
    0.35
     To
    0.34
     Consider
    0.34
     Am
    0.34
     Three
    0.34
     Most
    0.33
    Activations Density 4.661%

    No Known Activations