© 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. 40-GEMMASCOPE-2-RES-262K
    7. 131769
    Prev
    Next
    INDEX
    Explanations

    word following 're'

    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_40_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
     commercials
    0.39
     протягом
    0.39
     selama
    0.38
    ೆಯೇ
    0.38
    ंडर
    0.38
    異なります
    0.38
    넥
    0.38
    <unused2168>
    0.38
    从此
    0.37
     forever
    0.37
    POSITIVE LOGITS
     Retour
    0.38
     peripheral
    0.37
    Collection
    0.35
    Eleven
    0.35
     eventful
    0.35
     пери
    0.34
     handlerInput
    0.34
     توڑ
    0.33
    ôtel
    0.33
     evoked
    0.33
    Activations Density 0.000%

    No Known Activations