© 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. 18240
    Prev
    Next
    INDEX
    Explanations

    purpose, process, images, customer, us

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

    systems, domains, and specific entities

    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
     egli
    0.52
     Labour
    0.51
    ก
    0.51
     desconocido
    0.50
     Kompet
    0.49
     samedi
    0.49
     Nok
    0.48
     Duncan
    0.47
    𝘨
    0.47
    วงศ์
    0.46
    POSITIVE LOGITS
     FCM
    0.44
    ্ের
    0.43
    ጥረ
    0.43
    roidery
    0.43
     bottoms
    0.42
     nonatomic
    0.42
    otiv
    0.42
     repercussions
    0.41
    aloo
    0.41
    iteness
    0.41
    Activations Density 0.000%

    No Known Activations