© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 192790
    Prev
    Next
    INDEX
    Explanations

    faded, Somali, American

    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
     ordinairement
    0.38
     enfermed
    0.37
     مرد
    0.37
    瘸
    0.37
     rmse
    0.36
     materia
    0.35
     ዳ
    0.35
     ollut
    0.35
     guerra
    0.34
     (\%)
    0.34
    POSITIVE LOGITS
     skillset
    0.46
     talking
    0.44
     разговари
    0.44
    喜歡
    0.41
     megfelelő
    0.40
    باح
    0.40
    িলো
    0.39
     incentivize
    0.39
     contacting
    0.38
    ्हे
    0.38
    Activations Density 0.002%

    No Known Activations