© 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. 157744
    Prev
    Next
    INDEX
    Explanations

    entrepreneur, programmer, highest GDP, eternal covenant, Mr

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

    money tied to other things

    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
    isinde
    0.47
     movimento
    0.45
     eines
    0.45
    𝐽
    0.45
     njihov
    0.44
    ͌
    0.43
     یک
    0.42
     décider
    0.42
    icial
    0.42
     cáncer
    0.42
    POSITIVE LOGITS
     Guo
    0.48
     Climbing
    0.46
     丨
    0.45
     উচ্ছ
    0.45
     Wool
    0.43
    㴓
    0.43
     Fountain
    0.43
    ంద్
    0.43
    ForKey
    0.42
     overflows
    0.42
    Activations Density 0.000%

    No Known Activations