© 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. 3761
    Prev
    Next
    INDEX
    Explanations

    holding events

    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
    ᯾
    -1.73
     οποίο
    -1.71
     haremos
    -1.59
    敕
    -1.45
    哧
    -1.44
    尨
    -1.43
     podremos
    -1.43
    Ꭳ
    -1.40
    zeption
    -1.39
    Here
    -1.38
    POSITIVE LOGITS
    </strong>
    1.66
     in
    1.62
     gången
    1.59
    嗵
    1.58
     a
    1.58
    ")
    1.55
     If
    1.55
     egna
    1.54
     ‘
    1.48
     vše
    1.43
    Activations Density 0.032%

    No Known Activations