© 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. 93176
    Prev
    Next
    INDEX
    Explanations

    law legal advice

    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
     Classic
    0.44
     dedicated
    0.44
     Het
    0.44
     Magist
    0.44
    刘
    0.44
     quar
    0.43
     dedicata
    0.43
    ের
    0.43
     Acest
    0.43
     dedicato
    0.42
    POSITIVE LOGITS
     शहरा
    0.51
    हत्या
    0.51
    ख
    0.50
    <unused1169>
    0.49
    agers
    0.49
     электрон
    0.48
     smartest
    0.48
    든
    0.48
     journalists
    0.48
     filmmakers
    0.47
    Activations Density 0.005%

    No Known Activations