© 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. 99933
    Prev
    Next
    INDEX
    Explanations

    separation

    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
    اعة
    0.43
     smuggling
    0.38
    мора
    0.38
    дования
    0.37
     вывести
    0.36
     JE
    0.35
    сант
    0.35
    <td>
    0.35
    atera
    0.35
    irlik
    0.35
    POSITIVE LOGITS
     parting
    2.61
     parted
    2.52
     separation
    1.52
     séparation
    1.47
     separations
    1.45
     separación
    1.42
     Separation
    1.41
     separates
    1.38
     sépar
    1.36
     Separ
    1.35
    Activations Density 0.001%

    No Known Activations