© 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. 226114
    Prev
    Next
    INDEX
    Explanations

    firm believer, President Good

    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
    잍
    0.52
    екст
    0.51
     punctatis
    0.48
    ју
    0.47
    ныгы
    0.47
    チック
    0.46
     injunctive
    0.46
    젹
    0.46
    ᄄ
    0.45
    취
    0.44
    POSITIVE LOGITS
     vám
    0.52
     Mazda
    0.49
     বাজারে
    0.47
     lanz
    0.47
     Lexus
    0.46
    0
    0.46
    _{
    0.45
     lanza
    0.45
     grosse
    0.45
     alguien
    0.45
    Activations Density 0.000%

    No Known Activations