© 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-65K
    7. 3625
    Prev
    Next
    INDEX
    Explanations

    their. yours. my. his. its. our. their

    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
     може
    0.44
    Scrolling
    0.41
     purging
    0.41
    pleo
    0.41
    णारा
    0.41
     তোমার
    0.40
    দ্দি
    0.40
    杈
    0.40
    вен
    0.40
    다면
    0.39
    POSITIVE LOGITS
     themselves
    0.50
     അവരുടെ
    0.50
    उनकी
    0.50
     他们
    0.50
     उनकी
    0.47
     Mereka
    0.47
     त्यांच्या
    0.47
     their
    0.46
     தங்கள்
    0.46
     उनके
    0.46
    Activations Density 0.001%

    No Known Activations