© 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. 110482
    Prev
    Next
    INDEX
    Explanations

    money from Coca-Cola

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

    technical, computational, and conceptual descriptions

    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
     tathapi
    0.48
    뤄
    0.46
    saraba
    0.45
    érc
    0.45
    resolver
    0.44
     nende
    0.44
    еры
    0.44
     câ
    0.43
    कारी
    0.43
    কারে
    0.43
    POSITIVE LOGITS
    '
    0.68
    <0xBE>
    0.50
    <0xBB>
    0.48
    Perhaps
    0.48
     USA
    0.46
     Wheels
    0.46
     as
    0.46
     から
    0.44
     regress
    0.44
    两条
    0.44
    Activations Density 0.000%

    No Known Activations