© 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. 55933
    Prev
    Next
    INDEX
    Explanations

    EMA strategy crossover

    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
    replication
    0.42
    :
    0.42
    исленность
    0.41
    Adam
    0.41
    ின்றன
    0.40
    hardness
    0.40
    units
    0.40
     weaknesses
    0.40
    T
    0.39
    H
    0.39
    POSITIVE LOGITS
     하는
    0.44
     seconde
    0.43
     semble
    0.42
     свои
    0.42
    нії
    0.42
     wirtschaft
    0.42
     rehabilitate
    0.42
     entferne
    0.42
     égale
    0.41
     déclare
    0.41
    Activations Density 0.013%

    No Known Activations