© 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. 20356
    Prev
    Next
    INDEX
    Explanations

    digital microscope, charter bus, features, ®

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

    architecture concepts generating content

    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
     বৎসর
    0.41
    氩
    0.38
    Tienes
    0.38
     ή
    0.38
    称为
    0.37
    是一种
    0.37
    Bạn
    0.37
     fontWeight
    0.37
    𝑂
    0.36
     গ্রন্থ
    0.36
    POSITIVE LOGITS
     geopol
    0.40
     comunidad
    0.38
     sociales
    0.37
     community
    0.36
     brind
    0.36
     infrastrukt
    0.36
     comunidades
    0.36
    quela
    0.36
     nearby
    0.35
     Boko
    0.35
    Activations Density 0.352%

    No Known Activations