© 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. 22-GEMMASCOPE-RES-131K
    7. 70590
    Prev
    Next
    INDEX
    Explanations

    legal citations and technical descriptions

    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_22/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
    रीद
    -1.05
    מוז
    -0.96
    っていて
    -0.94
     Precinct
    -0.91
     ТО
    -0.90
    척
    -0.88
    dengar
    -0.88
    TokenNameRBRACE
    -0.87
     chô
    -0.85
    CURLOPT
    -0.84
    POSITIVE LOGITS
     to
    0.87
     that
    0.81
    uf
    0.81
    leggen
    0.78
    od
    0.77
     entsprechend
    0.77
    anz
    0.76
    滇
    0.75
    ukkig
    0.75
     towards
    0.74
    Activations Density 0.001%

    No Known Activations