© 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. 12094
    Prev
    Next
    INDEX
    Explanations

    list item markers

    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
     étrang
    -1.91
    鹛
    -1.75
    alakip
    -1.68
    boldmath
    -1.65
     rayures
    -1.58
    κι
    -1.53
    ticion
    -1.52
     jopa
    -1.51
     relâche
    -1.50
     kuin
    -1.46
    POSITIVE LOGITS
    -
    1.70
     his
    1.61
    -*
    1.45
    –
    1.35
     including
    1.29
     прид
    1.28
     beserta
    1.28
    thirds
    1.27
    **
    1.27
     A
    1.25
    Activations Density 0.010%

    No Known Activations