© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 211500
    Prev
    Next
    INDEX
    Explanations

    pairing and arriving

    np_acts-logits-general · gemini-2.5-flash-lite

    solubilityemployeetumorCelsiusEarthjoke

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    資産
    0.46
    ᵉ
    0.43
     financing
    0.43
    現金
    0.43
     agents
    0.39
     eventualmente
    0.39
    もあり
    0.39
     targeted
    0.39
    ≃
    0.39
     genuine
    0.39
    POSITIVE LOGITS
     Especific
    0.50
    荪
    0.48
     StreamReader
    0.47
     Tidak
    0.47
     Mem
    0.46
     Solo
    0.46
     దూర
    0.46
     پید
    0.45
    槑
    0.45
     Sempre
    0.44
    Activations Density 0.002%

    No Known Activations