© 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. 33552
    Prev
    Next
    INDEX
    Explanations

    numbers and lists

    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
    áld
    -0.88
    ärer
    -0.76
    מב
    -0.75
    bióticos
    -0.75
    Elsewhere
    -0.75
     with
    -0.74
    视着
    -0.74
     garçon
    -0.73
     so
    -0.72
    veless
    -0.72
    POSITIVE LOGITS
    slightly
    0.99
     SEVER
    0.90
    MEDIUM
    0.84
     Slightly
    0.84
    もう少し
    0.83
     sart
    0.81
     Seiko
    0.81
    indicates
    0.79
    ¹,
    0.78
     کمی
    0.78
    Activations Density 0.043%

    No Known Activations