© 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. 467
    Prev
    Next
    INDEX
    Explanations

    pronouns and Goods

    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
    なども
    0.33
    これも
    0.32
     and
    0.31
     zudem
    0.30
    也是
    0.30
    .
    0.30
    אן
    0.30
    各種
    0.29
    และ
    0.29
     причем
    0.29
    POSITIVE LOGITS
     όταν
    0.41
     imagine
    0.40
     WASTE
    0.38
     όσο
    0.38
    当我们
    0.37
     Someone
    0.36
     we
    0.36
     আমরা
    0.36
    有人
    0.36
     Когда
    0.35
    Activations Density 0.058%

    No Known Activations