© 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. 17991
    Prev
    Next
    INDEX
    Explanations

    Susanna, suspend, suspicious

    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
    几
    0.41
    acie
    0.38
    一遍
    0.37
    ництво
    0.37
    剂量
    0.37
    epat
    0.35
    乃
    0.34
    ulator
    0.34
     প্রাদেশিক
    0.34
    扎
    0.34
    POSITIVE LOGITS
     сус
    0.93
     SUS
    0.89
     susp
    0.87
    SUS
    0.86
    susp
    0.86
     suspend
    0.85
     sosp
    0.85
     sus
    0.84
    Sus
    0.82
     Sus
    0.80
    Activations Density 0.007%

    No Known Activations