© 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. 20977
    Prev
    Next
    INDEX
    Explanations

    problems with or related phrases

    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
     phénom
    -1.83
    ipzig
    -1.82
     anún
    -1.75
    鹪
    -1.66
    EdgeInsets
    -1.63
    
    -1.63
    螃
    -1.63
     出来
    -1.58
    ximity
    -1.58
     técn
    -1.58
    POSITIVE LOGITS
     with
    1.60
    或者
    1.58
     obyvateľov
    1.44
    特别是
    1.42
    </b>
    1.41
     związane
    1.41
     problems
    1.39
    ↵↵
    1.38
     initializing
    1.34
     którego
    1.33
    Activations Density 0.072%

    No Known Activations