© 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. 40600
    Prev
    Next
    INDEX
    Explanations

    neural networks and technical terms

    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
    鹧
    0.50
    iftoire
    0.46
     velocità
    0.44
    舂
    0.44
    ちょっと
    0.43
     довольно
    0.43
    大きな
    0.43
     مدينة
    0.42
     साधारण
    0.41
    ক্রান্ত
    0.41
    POSITIVE LOGITS
     issuers
    0.49
    ↵
    0.48
     predicate
    0.48
     livelihoods
    0.46
     assessors
    0.45
     eval
    0.44
     operand
    0.44
     you
    0.42
     factorization
    0.42
     predicated
    0.42
    Activations Density 0.002%

    No Known Activations