© 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. 110297
    Prev
    Next
    INDEX
    Explanations

    association of `research` with `associate`

    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
    //
    0.43
    束
    0.41
    まずは
    0.40
    лів
    0.39
     класу
    0.39
    ength
    0.38
    Issued
    0.38
     //
    0.37
    ewidth
    0.37
    至少
    0.37
    POSITIVE LOGITS
     eliminado
    0.45
     eccles
    0.45
    कालय
    0.44
    dienst
    0.44
    क्षम
    0.44
    elimin
    0.43
     подоб
    0.42
    eradish
    0.42
    𝘇
    0.42
    <0xBF>
    0.41
    Activations Density 0.002%

    No Known Activations