© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 3476
    Prev
    Next
    INDEX
    Explanations

    When they

    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_16k_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
    A
    0.48
    ς
    0.47
    面
    0.46
    ાઇ
    0.44
    的
    0.43
    *
    0.43
    Ex
    0.40
    λ
    0.40
    ed
    0.39
    ्स
    0.39
    POSITIVE LOGITS
     takePhotoButton
    0.47
     disseminating
    0.47
     rohkem
    0.46
     basilaires
    0.46
    땃
    0.44
     testaceis
    0.44
     پیغم
    0.43
     سکتے
    0.43
     plats
    0.43
    半島
    0.43
    Activations Density 0.060%

    No Known Activations