© 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. 4080
    Prev
    Next
    INDEX
    Explanations

    acts of escorting and convoying

    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
    telli
    -0.69
    หัว
    -0.65
    encodeWith
    -0.64
    (*(
    -0.64
     lụ
    -0.62
    кал
    -0.62
    COMO
    -0.61
     thập
    -0.61
    Sis
    -0.61
    hinged
    -0.61
    POSITIVE LOGITS
     escort
    6.13
     escorted
    4.88
     escor
    4.88
     Escort
    4.28
    Esc
    3.64
    esc
    3.58
     Escor
    3.56
     escrow
    3.00
     сопрово
    2.97
     escol
    2.89
    Activations Density 0.060%

    No Known Activations