© 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. 35015
    Prev
    Next
    INDEX
    Explanations

    Django forms questions

    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
    nasium
    -1.09
    .-.
    -1.02
     chale
    -1.01
     ensaio
    -0.98
    ooooooo
    -0.97
    chaik
    -0.96
     ktorí
    -0.96
     etui
    -0.96
    ariums
    -0.93
     konsumen
    -0.93
    POSITIVE LOGITS
    astă
    1.12
     tedy
    1.10
    蜗
    1.08
    ModelSerializer
    1.02
    écial
    1.02
     насеље
    1.00
    ceau
    1.00
    Ngay
    0.99
     хоче
    0.99
    tilizer
    0.97
    Activations Density 0.002%

    No Known Activations