© 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. 41295
    Prev
    Next
    INDEX
    Explanations

    multilingual 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
    leistungen
    0.46
    Ра
    0.45
     ස
    0.45
    pertoire
    0.44
     fielded
    0.43
     conso
    0.43
     структур
    0.42
     Ра
    0.41
     fared
    0.40
    рифмети
    0.40
    POSITIVE LOGITS
     yapılacak
    0.48
     nanotubes
    0.47
    ल्लू
    0.46
     waterways
    0.45
     straighten
    0.45
     chcesz
    0.43
    此
    0.43
     lipoprotein
    0.42
     move
    0.42
    办法
    0.41
    Activations Density 0.004%

    No Known Activations