© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72506
    Prev
    Next
    INDEX
    Explanations

    First of all

    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
     özellikle
    -1.53
     particularmente
    -1.49
     on
    -1.41
     específicamente
    -1.34
     incluyen
    -1.26
     
    -1.26
     見える
    -1.22
     especialmente
    -1.19
     éstas
    -1.18
     in
    -1.17
    POSITIVE LOGITS
    卨
    1.63
     this
    1.55
    While
    1.42
    鲔
    1.41
     utaf
    1.41
     aiut
    1.39
    鹩
    1.38
     cread
    1.38
    澆
    1.37
     bune
    1.35
    Activations Density 0.045%

    No Known Activations