© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1659
    Prev
    Next
    INDEX
    Explanations

    bolded words followed by definition

    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
    https
    0.38
    ोजना
    0.34
    nment
    0.33
    anzit
    0.33
     categ
    0.33
     २०२
    0.33
     https
    0.32
    📌
    0.32
     ChatGPT
    0.32
     covid
    0.31
    POSITIVE LOGITS
     Gölü
    0.37
     féd
    0.32
    knię
    0.32
     pě
    0.32
     liquefied
    0.31
    ёшь
    0.31
     dø
    0.31
    ógy
    0.30
     hátsó
    0.30
     স্টার
    0.30
    Activations Density 0.001%

    No Known Activations