© 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. 34-GEMMASCOPE-RES-131K
    7. 115912
    Prev
    Next
    INDEX
    Explanations

    IP addresses and networks

    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_34/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
    ெ
    -0.74
    ometric
    -0.73
    bilis
    -0.71
     Crop
    -0.70
    вание
    -0.69
     المق
    -0.69
    quinas
    -0.68
    enumii
    -0.68
    ashier
    -0.67
    ajaran
    -0.67
    POSITIVE LOGITS
     IPL
    1.13
     CID
    0.90
     Lotus
    0.87
     lotus
    0.77
     препратки
    0.77
    retrie
    0.76
     deal
    0.76
    Sectors
    0.74
     Deals
    0.74
     datastore
    0.73
    Activations Density 0.040%

    No Known Activations