© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47305
    Prev
    Next
    INDEX
    Explanations

    describing qualities or subsequent actions

    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
    {
    0.51
     athlete
    0.49
    伤
    0.46
     Testament
    0.42
    Section
    0.41
    Partition
    0.41
    be
    0.39
    partition
    0.38
    N
    0.38
    P
    0.38
    POSITIVE LOGITS
     chưa
    0.54
    xcsche
    0.50
    𐰑
    0.49
    واں
    0.49
     appass
    0.49
    釟
    0.47
    沏
    0.46
     accueill
    0.46
     REGIUNI
    0.46
     supermerc
    0.46
    Activations Density 0.002%

    No Known Activations