© 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. 5754
    Prev
    Next
    INDEX
    Explanations

    unethical or racist bot

    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
    τ
    0.46
     божомолдору
    0.46
    糈
    0.46
     चल
    0.43
    к
    0.42
    াস্থ্য
    0.41
     cục
    0.41
    RetResult
    0.41
    ϲ
    0.40
    tau
    0.40
    POSITIVE LOGITS
     principles
    0.52
     ants
    0.46
     decept
    0.46
     completely
    0.45
     passivation
    0.45
     guides
    0.44
     totalitarian
    0.44
     perfect
    0.44
     acceptance
    0.44
     anti
    0.44
    Activations Density 0.015%

    No Known Activations