© 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. 11524
    Prev
    Next
    INDEX
    Explanations

    not or never

    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
     a
    -1.27
     принято
    -1.23
    Hauteur
    -1.20
     beeintr
    -1.19
    ONESIA
    -1.18
     titular
    -1.16
     случайно
    -1.16
     endet
    -1.16
     disorganized
    -1.15
     soient
    -1.14
    POSITIVE LOGITS
     that
    1.89
     his
    1.75
     wszystkich
    1.39
    queous
    1.30
    //{
    1.30
    ”,
    1.30
    ='')
    1.30
    ditionally
    1.28
     bahkan
    1.27
     Türkei
    1.27
    Activations Density 0.048%

    No Known Activations