© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 40559
    Prev
    Next
    INDEX
    Explanations

    operations, feedback, and dispatch

    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
     άλ
    0.49
    ங்கல்
    0.49
    trä
    0.46
     gelegt
    0.45
    𝑔
    0.45
     ειδ
    0.45
    𝘭
    0.44
    bach
    0.44
     実
    0.44
    𝐠
    0.43
    POSITIVE LOGITS
    O
    0.46
    стива
    0.43
     fakat
    0.43
     Cafe
    0.42
    akuza
    0.42
     &
    0.41
     edeb
    0.40
     Oyun
    0.40
     theatre
    0.39
     ছাড়া
    0.38
    Activations Density 0.004%

    No Known Activations