© 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. 65747
    Prev
    Next
    INDEX
    Explanations

    numbers and place names

    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
     Quais
    -1.02
    olge
    -1.00
     nasz
    -0.98
     wszyst
    -0.98
    不错的
    -0.98
     fuertemente
    -0.97
    ždy
    -0.96
    眼泪
    -0.94
     Mejora
    -0.94
     sær
    -0.94
    POSITIVE LOGITS
     to
    0.98
     with
    0.96
     for
    0.93
     until
    0.93
    довал
    0.89
    textAlignment
    0.88
    jada
    0.88
    ৄ
    0.85
     metus
    0.84
    女的
    0.81
    Activations Density 0.005%

    No Known Activations