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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66514
    Prev
    Next
    INDEX
    Explanations

    particularly, accordance, terms, number, example, help, known

    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
     only
    -1.58
     like
    -1.31
    cheque
    -1.27
    Pojo
    -1.27
     passend
    -1.24
    only
    -1.23
    了两
    -1.23
    了一個
    -1.23
     Sebab
    -1.22
     perché
    -1.19
    POSITIVE LOGITS
     that
    1.77
    orsz
    1.42
     løpet
    1.36
     tillegg
    1.36
    UIControlState
    1.32
    韃
    1.30
     rowspan
    1.30
     UCLA
    1.27
     теперь
    1.26
     additional
    1.25
    Activations Density 1.284%

    No Known Activations