© 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. 40-GEMMASCOPE-2-RES-65K
    7. 239
    Prev
    Next
    INDEX
    Explanations

    Summer Street, llama-cpp-python, Huawei FreeBuds

    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_40_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
     atoms
    0.32
    ع
    0.30
    λα
    0.29
     rescuers
    0.28
    LOOK
    0.28
     patri
    0.28
    hematic
    0.27
    ammation
    0.27
    otopy
    0.27
    lique
    0.26
    POSITIVE LOGITS
    かもしれませんが
    0.33
     নীল
    0.31
     '['
    0.31
    股份有限公司
    0.30
     tetapi
    0.30
    openapi
    0.30
     Deloitte
    0.30
    ffmpeg
    0.30
    ...",
    0.30
    databinding
    0.30
    Activations Density 0.382%

    No Known Activations