© 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. 40-GEMMASCOPE-2-RES-262K
    7. 6344
    Prev
    Next
    INDEX
    Explanations

    remain unchanged

    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
    '
    0.39
     طریقے
    0.36
     lasciato
    0.34
    ูป
    0.33
     Leaving
    0.33
     عورت
    0.32
     NOW
    0.31
    濆
    0.31
    变得
    0.31
    Voici
    0.31
    POSITIVE LOGITS
     unchanged
    0.67
     intact
    0.59
     steadfast
    0.56
     tetap
    0.51
     elusive
    0.50
    ders
    0.49
     vigilant
    0.49
    unch
    0.48
     stubbornly
    0.46
     unsolved
    0.44
    Activations Density 0.005%

    No Known Activations