© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 29999
    Prev
    Next
    INDEX
    Explanations

    coding: utf-8 declarations

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    reusable
    -0.82
    typeout
    -0.79
    aine
    -0.76
     Esq
    -0.75
     empleo
    -0.75
     Inorg
    -0.75
    的高度
    -0.74
     löytyy
    -0.72
    ][/
    -0.71
    (":");
    -0.71
    POSITIVE LOGITS
    cp
    1.16
     cp
    1.10
    codecs
    1.06
     Errors
    1.05
     errors
    1.03
    Errors
    1.03
    errors
    1.02
     utf
    0.96
     codecs
    0.93
    encoding
    0.89
    Activations Density 0.047%

    No Known Activations