© 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. 41-GEMMASCOPE-2-RES-262K
    7. 101861
    Prev
    Next
    INDEX
    Explanations

    vacuum

    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_all/layer_41_width_262k_l0_big
    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
    splash
    0.45
     распростра
    0.44
    ReactNative
    0.44
     బయ
    0.43
    મત
    0.41
    重ね
    0.39
    淬
    0.39
    刷新
    0.39
    ปฏิ
    0.38
    璘
    0.38
    POSITIVE LOGITS
     vacuum
    1.73
     Vacuum
    1.59
    Vacuum
    1.59
     suction
    1.57
    vacuum
    1.53
     suck
    1.40
     vacu
    1.39
     sucking
    1.38
     sucked
    1.36
     hút
    1.29
    Activations Density 0.002%

    No Known Activations