© 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. 22-GEMMASCOPE-RES-131K
    7. 72205
    Prev
    Next
    INDEX
    Explanations

    order, Post, line, TB

    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_22/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
    ューズ
    -0.85
    ̎
    -0.85
    用に
    -0.81
    MAXN
    -0.81
    TBC
    -0.81
    xmlhttp
    -0.81
    СЯ
    -0.80
     لیے
    -0.79
    Plasmid
    -0.78
     Faça
    -0.76
    POSITIVE LOGITS
    場所は
    0.94
    литься
    0.92
    ISHING
    0.92
     میکن
    0.91
     did
    0.91
    逅
    0.91
    iendo
    0.89
     only
    0.89
     umgangssprach
    0.88
     until
    0.88
    Activations Density 0.057%

    No Known Activations