© 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. 40-GEMMASCOPE-2-RES-262K
    7. 190732
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns, descriptions, or actions

    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_40_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
     millennia
    0.40
     Image
    0.39
    防疫
    0.39
     IMAGE
    0.38
     Demonstration
    0.36
    歙
    0.36
     креп
    0.35
     Elections
    0.35
     du
    0.35
    国务
    0.35
    POSITIVE LOGITS
    orske
    0.43
    騙
    0.43
    endif
    0.40
    非
    0.40
    iii
    0.40
     შეიძლება
    0.39
    okka
    0.39
     spurious
    0.39
     fails
    0.39
     வாய்
    0.39
    Activations Density 0.001%

    No Known Activations