© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 98595
    Prev
    Next
    INDEX
    Explanations

    throw into

    np_acts-logits-general · gemini-2.5-flash-lite

    disrupting or affecting something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     equipments
    0.50
     distributing
    0.47
     白色
    0.47
     oa
    0.46
     夏
    0.45
     during
    0.45
     左
    0.45
     大型
    0.45
    二次
    0.45
     DURING
    0.44
    POSITIVE LOGITS
    புக
    0.52
     parable
    0.52
     phrasing
    0.51
     emphatically
    0.50
     pomo
    0.49
     dictum
    0.49
    ти
    0.48
     bloke
    0.46
    லக
    0.46
     zatem
    0.46
    Activations Density 0.010%

    No Known Activations