© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92679
    Prev
    Next
    INDEX
    Explanations

    lack of consent

    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_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
     I
    0.63
    ↵
    0.44
    staticmethod
    0.44
    I
    0.42
     unemployed
    0.40
     Problem
    0.40
     И
    0.40
    window
    0.39
     Instrumented
    0.39
     Instruments
    0.39
    POSITIVE LOGITS
    较高的
    0.50
    ței
    0.49
    ཌ
    0.48
    甴
    0.44
    ଶ
    0.43
    ând
    0.43
    燃烧
    0.43
    ्वती
    0.42
    讽
    0.42
    èo
    0.42
    Activations Density 0.017%

    No Known Activations