© 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. 210982
    Prev
    Next
    INDEX
    Explanations

    principal officer

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

    describing states and entities

    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
    经历
    0.48
    я
    0.48
    ใน
    0.47
    线条
    0.47
     γν
    0.46
    🧭
    0.46
     লক্ষ্যে
    0.46
     architectures
    0.46
    ק
    0.46
     类型
    0.45
    POSITIVE LOGITS
     otot
    0.42
    幼稚園
    0.40
     দুষ্ট
    0.40
     أثناء
    0.40
     turistas
    0.40
     kellett
    0.40
     sickly
    0.39
     لال
    0.38
    akaian
    0.38
     parlour
    0.38
    Activations Density 0.001%

    No Known Activations