© 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. 15195
    Prev
    Next
    INDEX
    Explanations

    titles starting with New or Introduction

    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
     kulak
    -1.25
     restoran
    -1.24
     bula
    -1.22
     autora
    -1.20
     aktor
    -1.17
     Código
    -1.11
     Compañía
    -1.09
     remé
    -1.09
     Política
    -1.08
    くれます
    -1.08
    POSITIVE LOGITS
     we
    1.49
    }=\
    1.29
     liegt
    1.14
    ]='\
    1.09
     that
    1.05
    有很多
    1.05
    枚目
    1.04
    ß
    1.03
    我們
    1.03
     reconocer
    1.02
    Activations Density 0.002%

    No Known Activations