© 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. 77291
    Prev
    Next
    INDEX
    Explanations

    contrast between abstract concepts

    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
     ጊዜ
    0.40
    >
    0.37
    Sponsored
    0.35
    🌺
    0.35
    >*
    0.35
    </
    0.34
     Canadi
    0.34
     Elev
    0.34
     Swim
    0.34
     궁금
    0.34
    POSITIVE LOGITS
     whereas
    1.64
    whereas
    1.55
     sedangkan
    1.45
     tandis
    1.36
     Whereas
    1.31
     Sedangkan
    1.28
    Whereas
    1.23
     natomiast
    1.12
    而
    1.11
     بينما
    1.10
    Activations Density 0.143%

    No Known Activations