© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129644
    Prev
    Next
    INDEX
    Explanations

    Corp, District 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
     Excise
    -0.99
    ciun
    -0.96
     colorear
    -0.96
    Біографія
    -0.95
     Capacitor
    -0.92
    یا
    -0.91
     Assyrian
    -0.91
     ストア
    -0.91
    tivitas
    -0.91
    foria
    -0.90
    POSITIVE LOGITS
     he
    1.15
     herself
    1.04
     his
    1.00
     him
    0.81
    やし
    0.78
    を見ながら
    0.76
     која
    0.76
    ŗ
    0.75
     programação
    0.75
    pack
    0.74
    Activations Density 0.095%

    No Known Activations