© 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. 59175
    Prev
    Next
    INDEX
    Explanations

    replacement or alternative items

    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
     измени
    -0.84
     lastly
    -0.81
     CHANG
    -0.80
    vités
    -0.79
     humedad
    -0.78
     измене
    -0.78
    дьми
    -0.78
     Changing
    -0.76
    arak
    -0.76
     Sanford
    -0.76
    POSITIVE LOGITS
     replacement
    6.34
     replacements
    5.59
    replacement
    5.13
    Replacement
    4.84
     Replacement
    4.72
    replace
    4.13
     replace
    4.09
    Replace
    3.75
     Replace
    3.69
     replaced
    3.61
    Activations Density 0.068%

    No Known Activations