© 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. 84722
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns this and that

    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
     сдела
    0.40
    蜍
    0.39
     Theater
    0.38
    做了
    0.38
     कहां
    0.38
    做
    0.37
    ючи
    0.37
    وں
    0.37
    ཐ
    0.37
    tych
    0.37
    POSITIVE LOGITS
     recognises
    0.49
    Whilst
    0.47
     éstos
    0.46
    جمالي
    0.45
     emphasises
    0.45
     timescales
    0.44
     adverts
    0.44
     emphasise
    0.44
     totalled
    0.43
     recognised
    0.43
    Activations Density 0.007%

    No Known Activations