© 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. 10-GEMMASCOPE-RES-131K
    7. 21890
    Prev
    Next
    INDEX
    Explanations

    achievable attainable doable

    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_10/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
    橚
    -2.64
    鵙
    -2.44
    </h2>
    -2.42
    釤
    -2.39
    stood
    -2.34
    是個
    -2.34
     valentín
    -2.30
    hahaha
    -2.28
    it
    -2.28
     député
    -2.27
    POSITIVE LOGITS
     They
    2.88
    ка
    2.22
     and
    2.22
     achievable
    2.20
     что
    2.13
     encontró
    2.13
     mereka
    2.11
    ¹.
    1.98
     These
    1.97
    CCIÓN
    1.95
    Activations Density 0.004%

    No Known Activations