© 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. 36015
    Prev
    Next
    INDEX
    Explanations

    allegedly

    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
    te
    0.56
     є
    0.53
    ata
    0.50
    nate
    0.49
     ва
    0.47
    ate
    0.46
    lose
    0.45
     dor
    0.45
    ia
    0.44
    factory
    0.44
    POSITIVE LOGITS
    据说
    0.50
     allegedly
    0.48
    다는
    0.47
    皘
    0.46
    వ్
    0.45
    الان
    0.45
    滩
    0.45
     Spiegel
    0.45
    Kako
    0.45
    الق
    0.44
    Activations Density 0.002%

    No Known Activations