© 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. 73085
    Prev
    Next
    INDEX
    Explanations

    else and elif

    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
    showed
    -1.23
     détruire
    -1.20
    happened
    -1.11
    Roi
    -1.07
    wasn
    -1.05
    cooking
    -1.05
    possessed
    -1.04
     nôtre
    -1.04
     Règlement
    -1.03
    explained
    -1.03
    POSITIVE LOGITS
     if
    1.38
    if
    1.27
     &
    1.22
    r
    1.17
    &
    1.12
    n
    1.06
    ?!
    1.02
    m
    1.02
    ne
    0.94
    {
    0.94
    Activations Density 0.001%

    No Known Activations