© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 184828
    Prev
    Next
    INDEX
    Explanations

    accounts, channel, curators, Secretary, trip

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

    threatening its

    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
    ५
    0.46
    なぜ
    0.46
    ll
    0.45
    สำคัญ
    0.45
     Hochzeit
    0.43
     retourner
    0.43
     Solids
    0.43
    𝒓
    0.43
    入力
    0.42
     Trên
    0.42
    POSITIVE LOGITS
     variegated
    0.54
     neighborhoods
    0.46
    anedi
    0.46
     closeness
    0.45
     supuesto
    0.44
    تي
    0.43
    odis
    0.43
     disagreements
    0.43
     arena
    0.43
     জীববিজ্ঞান
    0.43
    Activations Density 0.001%

    No Known Activations