© 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. 40226
    Prev
    Next
    INDEX
    Explanations

    border-radius and shadow

    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
    Only
    -1.36
    When
    -1.30
     these
    -1.28
    During
    -1.26
    These
    -1.23
     inapropiados
    -1.19
     During
    -1.16
    Typically
    -1.16
     When
    -1.15
    Generally
    -1.14
    POSITIVE LOGITS
     nabi
    1.30
     kredi
    1.26
     konfer
    1.22
    kemeja
    1.16
     sosi
    1.16
     crees
    1.16
    bottles
    1.15
    柠檬
    1.14
     eduk
    1.14
     edin
    1.13
    Activations Density 0.001%

    No Known Activations