© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 66994
    Prev
    Next
    INDEX
    Explanations

    Punjab and related places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recevrez
    -1.52
     svou
    -1.47
     devrez
    -1.45
    ある
    -1.34
    し
    -1.29
    は
    -1.20
     Arquite
    -1.20
     раздра
    -1.19
    𝓊
    -1.18
    就是
    -1.17
    POSITIVE LOGITS
    కర్య
    1.33
    可能的
    1.29
     mosso
    1.27
    ﻖ
    1.23
     of
    1.22
     forthcoming
    1.22
     möglicherweise
    1.21
     $^{
    1.21
    تمبر
    1.21
    orologio
    1.20
    Activations Density 0.037%

    No Known Activations