© 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. 28197
    Prev
    Next
    INDEX
    Explanations

    inviting presence after "join"

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

    Join us for

    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
     your
    0.52
    你们
    0.46
    僕
    0.45
     yourselves
    0.43
    ถาม
    0.43
    你的
    0.42
     my
    0.41
    僕は
    0.41
    uestros
    0.41
     僕
    0.41
    POSITIVE LOGITS
    ید
    0.52
    يته
    0.51
     domenica
    0.50
     percorso
    0.49
     giardino
    0.49
     sabato
    0.48
     iunie
    0.48
     ફિલ્મ
    0.47
     próximo
    0.46
    ِيم
    0.46
    Activations Density 0.019%

    No Known Activations