© 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. 175117
    Prev
    Next
    INDEX
    Explanations

    rent. wages. financial. institutions. groups

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

    hemorrhage or bleeding

    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
    Cam
    0.47
    -
    0.46
     শব্দটি
    0.46
     çalışmalar
    0.46
    UJ
    0.46
    Arizona
    0.46
    Dec
    0.45
    United
    0.45
     ise
    0.45
     جدید
    0.45
    POSITIVE LOGITS
    噤
    0.46
    賃
    0.46
    zuf
    0.46
     किराया
    0.45
    ఐ
    0.43
    ំណ
    0.43
     hemorrh
    0.43
    ೪
    0.43
    शक
    0.42
     berper
    0.42
    Activations Density 0.001%

    No Known Activations