© 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. 10996
    Prev
    Next
    INDEX
    Explanations

    things that are needed

    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
     lave
    0.41
    绥
    0.40
    otip
    0.40
     hum
    0.40
     canals
    0.40
    рати
    0.39
    ached
    0.39
    riera
    0.39
    шку
    0.38
    Blu
    0.37
    POSITIVE LOGITS
     उपाध्यक्ष
    0.42
     ശരീര
    0.39
     Shanks
    0.38
     अधिकतम
    0.37
    章
    0.37
    好奇
    0.37
     胸
    0.37
    预期
    0.36
     गर्लफ्रेंड
    0.36
     kyll
    0.36
    Activations Density 0.001%

    No Known Activations