© 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. 15287
    Prev
    Next
    INDEX
    Explanations

    programming code keywords like if

    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
    motorola
    -1.16
     acoged
    -1.08
     esclavos
    -1.06
     and
    -1.04
     bambú
    -1.02
     estabiliz
    -1.02
    siamo
    -1.01
     cómoda
    -1.00
     préparer
    -1.00
    efter
    -0.98
    POSITIVE LOGITS
     if
    1.06
     either
    1.01
     for
    1.00
    図
    0.89
    劇場
    0.88
     famiglia
    0.85
    当你
    0.84
    これからの
    0.82
    有些人
    0.82
    tom
    0.82
    Activations Density 0.006%

    No Known Activations