© 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. 26963
    Prev
    Next
    INDEX
    Explanations

    pilots initially

    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
     compliance
    0.52
    ，
    0.46
    德
    0.44
    ↵
    0.43
     security
    0.43
    รี
    0.43
    ный
    0.42
     dra
    0.42
     highway
    0.41
     itemtype
    0.41
    POSITIVE LOGITS
    ᚐ
    0.57
     Digit
    0.47
    goTo
    0.45
    getR
    0.45
     रिप्रोडक्शन
    0.44
     Zet
    0.44
    ಔ
    0.44
     ሥራ
    0.44
     Zoe
    0.43
     İş
    0.43
    Activations Density 0.003%

    No Known Activations