© 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. 34-GEMMASCOPE-RES-131K
    7. 108912
    Prev
    Next
    INDEX
    Explanations

    groups described as alike

    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
     and
    -1.12
     αυτά
    -0.89
    ുറ
    -0.88
     gedeelte
    -0.88
    性和
    -0.86
     allmäh
    -0.86
    hline
    -0.84
    SON
    -0.82
     Bank
    -0.82
    elen
    -0.82
    POSITIVE LOGITS
     alike
    8.13
    alike
    4.78
     gleicher
    3.31
    Alike
    3.14
     одина
    2.45
     כא
    2.31
     equally
    1.98
    一样
    1.96
    一樣
    1.77
     ALI
    1.74
    Activations Density 0.126%

    No Known Activations