© 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. 22-GEMMASCOPE-RES-131K
    4. 93069
    Prev
    Next
    INDEX
    Explanations

    ISSN and volume numbers

    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_22/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
    </b>
    -1.30
     sources
    -0.99
     same
    -0.98
     types
    -0.98
     vinh
    -0.97
    已是
    -0.96
    부터
    -0.96
     descrição
    -0.95
    I
    -0.94
     нескольких
    -0.94
    POSITIVE LOGITS
    Penulis
    1.17
    عية
    1.16
    خة
    1.15
    Влади
    1.10
    Suara
    1.05
    Kenapa
    1.01
     membersihkan
    1.01
    Veranstal
    0.99
    áne
    0.99
     during
    0.99
    Activations Density 0.001%

    No Known Activations