© 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. 10-GEMMASCOPE-RES-131K
    7. 101333
    Prev
    Next
    INDEX
    Explanations

    psychological states and challenges

    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
    ↵↵
    -1.34
    .
    -1.29
    无比
    -1.27
    8
    -1.26
    却被
    -1.26
     antonio
    -1.22
    3
    -1.20
     alamy
    -1.19
    vore
    -1.17
     marta
    -1.16
    POSITIVE LOGITS
     where
    1.68
     even
    1.48
    cakup
    1.44
     навіть
    1.44
     primeras
    1.41
     with
    1.38
     bolster
    1.35
    praš
    1.35
     expectativas
    1.35
    ganggu
    1.34
    Activations Density 0.086%

    No Known Activations