© 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. 184063
    Prev
    Next
    INDEX
    Explanations

    architecture and content

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

    domain name analysis

    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
     ಕುಟುಂಬ
    0.46
    toc
    0.45
     vállalat
    0.44
    ließlich
    0.44
    libc
    0.44
    Insight
    0.41
    Gesellschaft
    0.41
    <unused91>
    0.40
    ToBe
    0.40
    ದ್ಯ
    0.40
    POSITIVE LOGITS
     Architecture
    0.55
    ยม
    0.50
     Chicken
    0.47
     Campus
    0.46
     Architect
    0.46
     Buzz
    0.45
     buscar
    0.45
     Content
    0.45
    ย
    0.45
     Architektur
    0.44
    Activations Density 0.004%

    No Known Activations