© 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. 11028
    Prev
    Next
    INDEX
    Explanations

    keys, code, table, stereo

    np_acts-logits-general · gemini-2.5-flash-lite

    underscores in technical code and identifiers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     nueva
    -2.00
     \
    -1.99
     یک
    -1.88
    ⚋
    -1.81
     Geset
    -1.80
     Bedürfn
    -1.80
    橚
    -1.73
     accustomed
    -1.71
    struzioni
    -1.70
     has
    -1.69
    POSITIVE LOGITS
     Our
    2.11
    所有的
    1.68
     Other
    1.67
    嚀
    1.65
    跸
    1.64
    9
    1.62
    7
    1.60
    
    1.59
     diariamente
    1.59
     Including
    1.59
    Activations Density 0.109%

    No Known Activations