© 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. 21000
    Prev
    Next
    INDEX
    Explanations

    vectors and their properties

    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
     championships
    0.49
    淀
    0.47
    DISK
    0.46
     CHAIRMAN
    0.45
    disk
    0.45
    menuStrip
    0.44
    🍚
    0.44
    🍳
    0.44
    eventName
    0.44
     penyeleng
    0.43
    POSITIVE LOGITS
     vector
    2.58
     vectors
    2.58
     Vector
    2.28
     Vectors
    2.28
     vektor
    2.22
    Vector
    2.20
    向量
    2.20
     벡터
    2.20
    vectors
    2.16
    vector
    2.11
    Activations Density 0.041%

    No Known Activations