© 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. 56034
    Prev
    Next
    INDEX
    Explanations

    ever harm, rms signal, can predict

    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
     rượu
    0.44
     личности
    0.44
     szület
    0.44
     άλλα
    0.44
     nicknames
    0.43
     viande
    0.42
     forefathers
    0.42
    눗
    0.42
    科学家
    0.42
     Bible
    0.42
    POSITIVE LOGITS
    technology
    0.52
    greencar
    0.46
    integration
    0.43
    餐廳
    0.42
    integrate
    0.42
    electrical
    0.42
    ਏ
    0.41
    energy
    0.41
    NEST
    0.41
    upstream
    0.41
    Activations Density 0.029%

    No Known Activations