© 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. 27623
    Prev
    Next
    INDEX
    Explanations

    example demonstration using words

    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
     lave
    -1.04
    밑
    -0.96
     gard
    -0.94
     ALT
    -0.93
     oll
    -0.93
     ہیں
    -0.92
    ubereitung
    -0.90
     attire
    -0.90
    каче
    -0.88
     aks
    -0.87
    POSITIVE LOGITS
    事例
    1.34
     dimost
    1.33
     examples
    1.28
     Examples
    1.20
     Example
    1.19
     demuestra
    1.18
     using
    1.14
     demonstrate
    1.13
     demonstrating
    1.13
    Пример
    1.08
    Activations Density 0.044%

    No Known Activations