© 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. 70963
    Prev
    Next
    INDEX
    Explanations

    variational principle determining components

    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
     питання
    0.45
     energies
    0.44
     senses
    0.42
    ensation
    0.42
     ۳
    0.41
     القيم
    0.41
    preuves
    0.41
    怙
    0.40
     Arena
    0.40
    ĝ
    0.40
    POSITIVE LOGITS
     headquartered
    0.50
     wilfully
    0.48
     acet
    0.43
     presently
    0.41
     certified
    0.41
    、「
    0.41
     abiert
    0.41
     destined
    0.41
     principally
    0.41
     certific
    0.40
    Activations Density 0.003%

    No Known Activations