© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35456
    Prev
    Next
    INDEX
    Explanations

    mathematics and code structures

    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
     &
    -1.14
    ilions
    -0.98
    siempre
    -0.86
     suéter
    -0.85
    pueden
    -0.85
     ответить
    -0.84
     poesía
    -0.82
     simplifié
    -0.82
     ovlád
    -0.82
     Slovenia
    -0.81
    POSITIVE LOGITS
     filma
    0.90
    ❧
    0.86
     Waite
    0.83
     hant
    0.83
    posição
    0.83
     привы
    0.83
     sini
    0.82
    aż
    0.82
    ÄT
    0.82
     unfortunate
    0.82
    Activations Density 0.024%

    No Known Activations