© 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. 221
    Prev
    Next
    INDEX
    Explanations

    smooth manifolds

    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
    5
    -1.97
    7
    -1.93
    8
    -1.90
    0
    -1.57
    1
    -1.52
    6
    -1.48
     ");
    -1.34
     follows
    -1.24
     getNombre
    -1.21
     ambayo
    -1.20
    POSITIVE LOGITS
    あなたは
    1.52
    ynchronously
    1.45
     of
    1.40
    堝
    1.40
    שלום
    1.40
    istically
    1.39
    ◆◆
    1.38
     muros
    1.38
    前回の
    1.38
    ――――
    1.38
    Activations Density 0.043%

    No Known Activations