© 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. 649
    Prev
    Next
    INDEX
    Explanations

    numbers, lists, and structures

    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
    ताएं
    0.50
    ل
    0.50
    കാല
    0.49
    Black
    0.48
    ล
    0.46
     extravaganza
    0.46
    .|__
    0.46
    其他
    0.45
    यात्रा
    0.45
    NAB
    0.44
    POSITIVE LOGITS
     soldados
    0.42
    iforme
    0.41
     previo
    0.41
    ராட்சி
    0.41
     평가
    0.40
    aranam
    0.39
     fragment
    0.39
     фраг
    0.39
     chi
    0.38
     ಕಂಡ
    0.38
    Activations Density 0.000%

    No Known Activations