© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71039
    Prev
    Next
    INDEX
    Explanations

    followed by other

    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
    bước
    -1.13
     когато
    -1.00
     when
    -1.00
     когда
    -1.00
     derfor
    -0.99
     которых
    -0.97
    During
    -0.94
    Миха
    -0.92
    Когда
    -0.90
    larında
    -0.90
    POSITIVE LOGITS
     followed
    2.06
    followed
    1.57
     other
    1.46
     others
    1.43
    Followed
    1.31
     diğer
    1.16
     سایر
    1.13
     остальных
    1.12
     Followed
    1.11
    fo
    1.06
    Activations Density 0.028%

    No Known Activations