© 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. 31-GEMMASCOPE-2-RES-65K
    7. 12113
    Prev
    Next
    INDEX
    Explanations

    applies only

    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_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
    enson
    0.41
     శా
    0.39
     जनता
    0.38
     كث
    0.37
     constamment
    0.37
    rakash
    0.37
    ந
    0.36
    ຮ
    0.36
    を目
    0.36
     constantemente
    0.36
    POSITIVE LOGITS
     applies
    0.64
    適用
    0.57
     only
    0.55
     correspondingly
    0.54
    适用于
    0.53
     apply
    0.52
    针对
    0.52
     applied
    0.52
     Applies
    0.52
     hanya
    0.51
    Activations Density 0.557%

    No Known Activations