© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71691
    Prev
    Next
    INDEX
    Explanations

    public sealed class

    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
     genannten
    -0.97
     that
    -0.97
    久し
    -0.86
    Also
    -0.85
    凄く
    -0.82
    回家
    -0.81
    がんば
    -0.81
    できるだけ
    -0.81
    Från
    -0.81
     допомогою
    -0.80
    POSITIVE LOGITS
    gató
    0.99
    ácidos
    0.98
    ochond
    0.96
    ')),
    0.94
    wisata
    0.94
     възможно
    0.94
    aliyet
    0.94
    лили
    0.93
    ордина
    0.93
    letic
    0.93
    Activations Density 0.000%

    No Known Activations