© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2281
    Prev
    Next
    INDEX
    Explanations

    ability of / to; inability of / to

    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
     negociaciones
    -1.43
     aislada
    -1.28
     embarazada
    -1.20
    絝
    -1.18
     gruesa
    -1.16
     республики
    -1.14
     dureza
    -1.13
     exitosa
    -1.13
    alamualaikum
    -1.13
     srdce
    -1.13
    POSITIVE LOGITS
     of
    9.50
    ของ
    4.84
     của
    4.19
     של
    3.31
     των
    2.67
    ของคุณ
    2.30
    of
    2.19
    もちろん
    1.86
     του
    1.84
     Of
    1.65
    Activations Density 0.231%

    No Known Activations