© 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. 34-GEMMASCOPE-RES-131K
    7. 49066
    Prev
    Next
    INDEX
    Explanations

    android specific terms

    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
    zo
    -0.66
     erinnern
    -0.66
    figsize
    -0.66
    ĵ
    -0.66
    rawValue
    -0.65
    فتح
    -0.65
    cerr
    -0.64
    lhs
    -0.64
    ждают
    -0.64
    <thead>
    -0.62
    POSITIVE LOGITS
    ̦
    0.70
     Waller
    0.69
     Vendor
    0.68
    
    0.68
     delegation
    0.66
    rra
    0.66
    dard
    0.66
     cavalry
    0.66
    Wd
    0.66
     camp
    0.65
    Activations Density 0.067%

    No Known Activations