© 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. 22-GEMMASCOPE-RES-131K
    7. 54101
    Prev
    Next
    INDEX
    Explanations

    email addresses and organizational identifiers

    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
     recklessly
    -1.27
     установка
    -1.24
    ьогодні
    -1.22
     zařízení
    -1.22
     ชุด
    -1.20
    
    -1.17
    fahrzeug
    -1.16
     ปี
    -1.16
    〣
    -1.16
    nige
    -1.13
    POSITIVE LOGITS
     Although
    1.32
     although
    1.30
     both
    1.30
     same
    1.26
     mostly
    1.20
     Because
    1.16
    توضیحات
    1.14
     Since
    1.13
     mainly
    1.10
     primarily
    1.07
    Activations Density 0.021%

    No Known Activations