© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 40598
    Prev
    Next
    INDEX
    Explanations

    foundational descriptors and actions

    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
    汽車
    0.39
     tossing
    0.38
     pitching
    0.37
    -<
    0.37
    模様
    0.36
     tossed
    0.36
     automobiles
    0.36
     tosses
    0.36
     bodily
    0.35
     অবস্থান
    0.35
    POSITIVE LOGITS
    </h1>
    0.45
     liberate
    0.44
    מיד
    0.41
    contre
    0.39
    tableView
    0.38
    BACK
    0.38
    ಾಲ
    0.38
    FREQ
    0.37
    änz
    0.36
    теры
    0.36
    Activations Density 0.001%

    No Known Activations