© 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. 31-GEMMASCOPE-2-RES-262K
    7. 30407
    Prev
    Next
    INDEX
    Explanations

    place, system, loop, know, one

    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
     partying
    0.43
    5
    0.41
    ]."
    0.39
    7
    0.38
    reverse
    0.38
     steaming
    0.38
     romp
    0.37
     abroad
    0.37
     $"
    0.37
     comunidades
    0.37
    POSITIVE LOGITS
     місто
    0.49
     जेव्हा
    0.47
     завжди
    0.45
     найкра
    0.45
     только
    0.45
     всегда
    0.45
    的时候
    0.44
     বাঁচ
    0.44
     Escherichia
    0.44
     ഒരിക്ക
    0.43
    Activations Density 0.006%

    No Known Activations