© 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. 34-GEMMASCOPE-RES-131K
    7. 45212
    Prev
    Next
    INDEX
    Explanations

    purchased, installed, replaced

    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_34/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
    ()]
    -1.00
    ">*
    -0.96
     Natalie
    -0.92
    ()}
    -0.92
     depreciation
    -0.91
    આ
    -0.90
     létre
    -0.88
    )]
    -0.88
    ämän
    -0.88
    में
    -0.87
    POSITIVE LOGITS
     replaced
    1.40
     replace
    1.38
     purchased
    1.38
     bought
    1.37
     replaces
    1.28
     purchase
    1.22
     put
    1.17
     ordered
    1.15
     installed
    1.15
     replacing
    1.14
    Activations Density 0.028%

    No Known Activations