© 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. 34-GEMMASCOPE-RES-131K
    7. 31649
    Prev
    Next
    INDEX
    Explanations

    templating language delimiters

    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
    Not in Any Lists

    No Comments

    Negative Logits
     olej
    -0.91
     univerz
    -0.90
     baterie
    -0.90
     kabát
    -0.89
     akci
    -0.88
     architekt
    -0.88
     kapac
    -0.86
     histó
    -0.86
     konkuren
    -0.84
    Ding
    -0.84
    POSITIVE LOGITS
     if
    1.54
    if
    1.43
     for
    1.40
    for
    1.08
     include
    1.06
    else
    1.04
    php
    0.95
     each
    0.93
     If
    0.90
     For
    0.88
    Activations Density 0.056%

    No Known Activations