© 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. 153830
    Prev
    Next
    INDEX
    Explanations

    SIZE of, Patient Monitoring, vitamin B, clients, Industry

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

    intellectual entertainment

    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
    阻止
    0.51
    防治
    0.47
    認識
    0.46
    救援
    0.46
    Ĕ
    0.46
     प्रदूषण
    0.45
    禣
    0.45
    測試
    0.44
    错误的
    0.44
     Renewable
    0.42
    POSITIVE LOGITS
    eliers
    0.54
    ieri
    0.51
    érables
    0.50
     elles
    0.48
    როს
    0.48
     iterates
    0.46
    яз
    0.46
     occasions
    0.46
     immers
    0.46
    orges
    0.46
    Activations Density 0.000%

    No Known Activations