© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26313
    Prev
    Next
    INDEX
    Explanations

    project

    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_22/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
     when
    -1.21
     or
    -1.11
     keberadaan
    -1.07
     for
    -1.02
    あくまで
    -0.99
    恂
    -0.96
    льність
    -0.96
     sejumlah
    -0.95
     pemilihan
    -0.94
     because
    -0.93
    POSITIVE LOGITS
    ใ
    1.15
     erin
    1.11
     somma
    1.09
     alho
    1.08
    κει
    1.04
     offerte
    1.02
     clienti
    1.01
     män
    1.01
     kado
    1.01
     学习
    1.00
    Activations Density 0.066%

    No Known Activations