© 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-262K
    7. 138527
    Prev
    Next
    INDEX
    Explanations

    code imports and program structures

    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
     candle
    0.46
     besieged
    0.42
    ון
    0.41
     detoxification
    0.41
     swift
    0.40
     electrom
    0.40
     electromagnetic
    0.39
     {
    0.39
     conformation
    0.39
     transporting
    0.39
    POSITIVE LOGITS
     낮은
    0.47
     déchets
    0.46
     Вул
    0.45
     കാല
    0.44
     மாசுபாடு
    0.44
     Buccaneers
    0.44
     बढ़ाता
    0.44
    Trash
    0.44
     للأ
    0.42
     மாசுபா
    0.42
    Activations Density 0.009%

    No Known Activations