© 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. 204477
    Prev
    Next
    INDEX
    Explanations

    work and career descriptions

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

    character creation

    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
    =>{
    0.54
    飽
    0.50
    τή
    0.45
    航
    0.44
     manures
    0.44
    出
    0.44
    会話
    0.43
    寿
    0.43
    希望
    0.42
    ಗೊಳ
    0.42
    POSITIVE LOGITS
     +
    0.58
     sistema
    0.55
    sistema
    0.52
    lardı
    0.51
     formando
    0.48
     ),
    0.47
    SECOND
    0.47
     delantero
    0.47
     Second
    0.46
     Segundo
    0.45
    Activations Density 0.000%

    No Known Activations