© 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. 116855
    Prev
    Next
    INDEX
    Explanations

    profitability, status, biennium

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

    greenhouse effect

    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
    サ
    0.52
     Cables
    0.50
     ～
    0.49
    なくなった
    0.49
    Après
    0.48
    ～～
    0.45
     Cem
    0.45
    捍
    0.45
     Zusätzlich
    0.44
    ゚
    0.44
    POSITIVE LOGITS
     urm
    0.49
     bulan
    0.48
     rmse
    0.47
     neste
    0.46
     xu
    0.46
     yardımcı
    0.46
    owns
    0.44
    amily
    0.43
    urdu
    0.43
    amino
    0.43
    Activations Density 0.003%

    No Known Activations