© 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-65K
    7. 35712
    Prev
    Next
    INDEX
    Explanations

    names and foreign phrases

    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_65k_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
    cknowledg
    0.40
    tena
    0.40
     především
    0.40
    unächst
    0.40
    ம்தா
    0.39
    ─────
    0.39
    𝑳
    0.39
    Trước
    0.38
    apabb
    0.38
    <unused476>
    0.38
    POSITIVE LOGITS
     tags
    0.44
     cable
    0.42
     metric
    0.42
     trade
    0.40
     table
    0.39
     data
    0.39
     exchange
    0.38
    也
    0.38
     solutions
    0.38
     pliers
    0.38
    Activations Density 0.018%

    No Known Activations