© 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-262K
    7. 111727
    Prev
    Next
    INDEX
    Explanations

    features, tools, release dates

    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_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
     நா
    0.40
    âng
    0.39
    hendis
    0.37
    ᒍ
    0.36
    vertices
    0.36
     लै
    0.36
    óng
    0.35
    eneg
    0.35
    Volumes
    0.35
     kř
    0.35
    POSITIVE LOGITS
    covariance
    0.40
     palliative
    0.37
    秝
    0.37
     tocar
    0.36
    借助
    0.36
     covariance
    0.36
    Commissioner
    0.36
    ฬา
    0.36
    Migrations
    0.35
     compresses
    0.35
    Activations Density 0.000%

    No Known Activations