© 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. 36761
    Prev
    Next
    INDEX
    Explanations

    chatbots and power

    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
     रहेगा
    0.45
    Cities
    0.44
    Choices
    0.44
    蛩
    0.43
    Drive
    0.42
     প্রয়োজন
    0.42
    Goals
    0.42
    AL
    0.41
    ં
    0.41
    的具体
    0.41
    POSITIVE LOGITS
     decent
    0.51
     poder
    0.50
     oppressed
    0.48
     vault
    0.47
     peaceful
    0.47
     mycop
    0.45
     antivirus
    0.45
     headset
    0.44
     foreigner
    0.44
     inhalation
    0.44
    Activations Density 0.002%

    No Known Activations