© 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. 182302
    Prev
    Next
    INDEX
    Explanations

    legal acts and proceedings

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

    simple description

    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
     बांग्लादेश
    0.45
    🗻
    0.45
     سایر
    0.45
     bû
    0.45
     त्यासाठी
    0.43
    <0x91>
    0.43
    💒
    0.42
    veld
    0.42
     spf
    0.41
     Gesù
    0.41
    POSITIVE LOGITS
     uptake
    0.44
    ShowWindow
    0.43
    ExpireTime
    0.43
     táo
    0.42
    ₹
    0.41
     exportation
    0.41
    SendData
    0.40
    ARROW
    0.39
    FUNC
    0.39
    CHA
    0.38
    Activations Density 0.001%

    No Known Activations