© 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. 10-GEMMASCOPE-RES-131K
    4. 10070
    Prev
    Next
    INDEX
    Explanations

    many other

    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
     but
    -1.88
    ingale
    -1.45
     мозга
    -1.41
     pulseira
    -1.41
    kespea
    -1.39
    rists
    -1.38
    خوب
    -1.38
     одном
    -1.37
    worldly
    -1.34
     amortecedor
    -1.34
    POSITIVE LOGITS
     other
    3.89
     других
    2.53
     anderen
    2.50
     innych
    2.34
     weiteren
    2.22
     others
    2.17
     دیگر
    2.16
     diğer
    2.14
     that
    2.11
    其他
    2.08
    Activations Density 0.040%

    No Known Activations