© 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. 65563
    Prev
    Next
    INDEX
    Explanations

    placeholder 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
     sabias
    -0.94
     بشر
    -0.93
    сс
    -0.91
     vermelha
    -0.88
     observed
    -0.87
    equilibrio
    -0.87
     akal
    -0.87
     zimowe
    -0.86
     multiuso
    -0.86
     ortodo
    -0.86
    POSITIVE LOGITS
     -
    1.00
     dürfen
    0.92
     asamblea
    0.81
    这话
    0.81
    b
    0.78
    小学校
    0.78
     ―
    0.77
     حتی
    0.77
     ".
    0.76
     relent
    0.76
    Activations Density 0.012%

    No Known Activations