© 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-65K
    7. 48293
    Prev
    Next
    INDEX
    Explanations

    numbers, mathematical symbols, letters

    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_65k_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
     dentistry
    0.49
     dentists
    0.49
     organism
    0.43
    Ν
    0.42
     fermionic
    0.40
     lysates
    0.39
     earthenware
    0.39
     aberr
    0.39
     dental
    0.39
    年も
    0.38
    POSITIVE LOGITS
    єю
    0.47
     কালি
    0.47
    ocarpus
    0.46
     Akash
    0.44
    苌
    0.44
    insic
    0.44
    ünftig
    0.43
    étant
    0.43
    dari
    0.42
     acus
    0.42
    Activations Density 0.001%

    No Known Activations