© 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. 49541
    Prev
    Next
    INDEX
    Explanations

    stamps and commemorative coins

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

    stamps, postal, banknotes

    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
    钣
    0.67
    报告
    0.46
    电器
    0.46
    斫
    0.45
    InputDir
    0.45
    沥
    0.45
     প্রস
    0.44
    龄
    0.44
    对手
    0.44
     userInput
    0.44
    POSITIVE LOGITS
     stamps
    0.79
     postal
    0.75
    Postal
    0.72
    postal
    0.71
     Postal
    0.69
     stamp
    0.64
     commemorative
    0.64
     डाक
    0.63
     Stamps
    0.63
    issued
    0.58
    Activations Density 0.050%

    No Known Activations