© 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. 92863
    Prev
    Next
    INDEX
    Explanations

    tape, Copenhagen, communication

    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
    ירות
    0.47
    Я
    0.46
     Paragu
    0.45
     তরফে
    0.45
    Autor
    0.45
     aihe
    0.45
    נ
    0.44
     Souls
    0.43
    Assumption
    0.42
    诸
    0.42
    POSITIVE LOGITS
    ্কে
    0.46
    tape
    0.44
     taping
    0.44
     future
    0.43
     tapes
    0.43
    Tape
    0.43
    的
    0.43
     là
    0.42
     μετά
    0.42
    нің
    0.42
    Activations Density 0.002%

    No Known Activations