© 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. 54028
    Prev
    Next
    INDEX
    Explanations

    aim of the study

    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
     kræ
    -0.85
     adım
    -0.84
    ്
    -0.81
    etton
    -0.77
     Hoa
    -0.77
    匪
    -0.76
     ethnographic
    -0.75
     Я
    -0.74
     зато
    -0.73
     Cou
    -0.73
    POSITIVE LOGITS
    viewHolder
    0.88
    Gdzie
    0.86
     lemn
    0.86
     morto
    0.84
     Rektor
    0.84
    テレビ
    0.83
     Intens
    0.83
     Helpful
    0.83
     utile
    0.82
     защиты
    0.81
    Activations Density 0.113%

    No Known Activations