© 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. 8126
    Prev
    Next
    INDEX
    Explanations

    years ending in 9

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

    years and decades

    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
    ো
    0.42
    কে
    0.40
    os
    0.40
    糉
    0.40
    و
    0.39
     människ
    0.38
     roupa
    0.37
     कोणी
    0.37
     மொத்தம்
    0.36
     ntawm
    0.36
    POSITIVE LOGITS
    .
    0.40
    ineties
    0.40
     eighties
    0.39
     década
    0.39
     early
    0.37
     начало
    0.36
     sixties
    0.36
    писи
    0.36
     веке
    0.36
    century
    0.36
    Activations Density 0.090%

    No Known Activations