© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73730
    Prev
    Next
    INDEX
    Explanations

    at URL

    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
     residency
    -1.27
    idency
    -1.07
     Residency
    -0.96
     residen
    -0.92
     residence
    -0.86
     residences
    -0.78
     résidence
    -0.78
     سفر
    -0.77
     residencia
    -0.76
     righteousness
    -0.75
    POSITIVE LOGITS
    мма
    0.74
     Hendrik
    0.74
    imals
    0.73
     $\|
    0.72
     appraisal
    0.71
    }=\{
    0.68
    钩
    0.68
    endix
    0.66
     құ
    0.66
    wuchs
    0.65
    Activations Density 0.026%

    No Known Activations