© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 87218
    Prev
    Next
    INDEX
    Explanations

    behavior trees and AI logic

    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_16_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
    aju
    0.67
    .
    0.56
    su
    0.51
    sa
    0.48
    osi
    0.48
    ائن
    0.47
     للا
    0.47
     piel
    0.46
     fina
    0.46
    الإ
    0.46
    POSITIVE LOGITS
     helped
    0.54
    孅
    0.52
     Helped
    0.52
     eradicated
    0.51
     中古
    0.50
    кр
    0.50
     जीतकर
    0.50
    ား
    0.49
     carefree
    0.49
    wearing
    0.49
    Activations Density 0.000%

    No Known Activations