© 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. 77130
    Prev
    Next
    INDEX
    Explanations

    Copyright

    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
     نشان
    -0.76
    }</
    -0.75
     reconn
    -0.73
     urchin
    -0.73
     میں
    -0.73
    ],\
    -0.73
     PCV
    -0.72
     Lafayette
    -0.72
    enegro
    -0.72
     igualdad
    -0.71
    POSITIVE LOGITS
    ᐈ
    0.66
    凶
    0.66
    vací
    0.64
     Depot
    0.63
    Chicago
    0.63
    了一会儿
    0.63
    omaterial
    0.63
     способом
    0.62
    HttpMethod
    0.61
    話は
    0.60
    Activations Density 0.030%

    No Known Activations