© 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. 108139
    Prev
    Next
    INDEX
    Explanations

    key information

    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
     penghar
    -1.05
     hidupnya
    -0.99
     pemikiran
    -0.94
     kenyataan
    -0.91
     円
    -0.88
     perbuatan
    -0.86
    zdě
    -0.85
     suasana
    -0.82
    𝐳
    -0.82
    atorium
    -0.79
    POSITIVE LOGITS
     key
    6.75
    key
    5.22
    Key
    4.44
     Key
    4.34
     keys
    4.13
    KEY
    4.09
     KEY
    3.88
     ключ
    3.77
     ключе
    3.64
    关键
    3.55
    Activations Density 0.052%

    No Known Activations