© 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. 128301
    Prev
    Next
    INDEX
    Explanations

    names of politicians and scientists

    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
     nagu
    -1.07
     like
    -1.00
    ️⃣
    -0.96
    .-(
    -0.96
    toner
    -0.95
    درسة
    -0.93
    tarte
    -0.93
     aktor
    -0.91
    zku
    -0.90
    ٹر
    -0.90
    POSITIVE LOGITS
    super
    1.02
     interesting
    0.93
    not
    0.90
    ok
    0.89
    am
    0.86
    now
    0.85
    ju
    0.84
    的说道
    0.84
    ay
    0.83
    add
    0.82
    Activations Density 0.000%

    No Known Activations