© 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. 33049
    Prev
    Next
    INDEX
    Explanations

    without directly holding

    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
     stir
    0.49
     Stir
    0.47
     Zeitschr
    0.46
     bimod
    0.46
    nade
    0.46
    ismod
    0.45
    浯
    0.45
    neys
    0.45
     oprav
    0.44
    ophiles
    0.44
    POSITIVE LOGITS
    FIFA
    0.46
    NFT
    0.44
     year
    0.42
     player
    0.42
    YouTube
    0.40
    リューション
    0.40
    ськ
    0.40
     pageant
    0.39
    N
    0.39
    ∪
    0.39
    Activations Density 0.003%

    No Known Activations