© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124148
    Prev
    Next
    INDEX
    Explanations

    lack of

    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
    黢
    -1.84
     monstre
    -1.84
     resté
    -1.81
    تیجه
    -1.81
     grotte
    -1.77
    簟
    -1.77
    橚
    -1.74
    かした
    -1.73
     guitare
    -1.69
    魠
    -1.69
    POSITIVE LOGITS
    t
    1.56
     which
    1.55
     urgent
    1.55
     obvious
    1.54
     equal
    1.45
    的所有
    1.45
     ability
    1.43
     What
    1.43
    =@"
    1.41
    了他
    1.38
    Activations Density 0.029%

    No Known Activations