© 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. 34-GEMMASCOPE-RES-131K
    7. 93051
    Prev
    Next
    INDEX
    Explanations

    blend of styles

    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_34/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
    groupName
    -0.86
    tijds
    -0.80
     sienten
    -0.80
     iglesias
    -0.77
     倍
    -0.74
    Zunanje
    -0.74
     الموت
    -0.74
    greenrobot
    -0.73
    openhauer
    -0.73
    vocation
    -0.73
    POSITIVE LOGITS
     blend
    3.88
     fusion
    3.53
     blending
    3.50
     mix
    3.36
     merge
    3.31
     merging
    3.28
     combining
    3.19
    融合
    3.08
    blend
    3.08
     mixing
    3.08
    Activations Density 0.076%

    No Known Activations