© 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. 108229
    Prev
    Next
    INDEX
    Explanations

    subjective experience or report

    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
    ztyn
    -0.80
    ิ่ง
    -0.79
    一首
    -0.76
     vacation
    -0.73
    ORCID
    -0.72
     silen
    -0.71
    jl
    -0.70
     synthesizer
    -0.69
    Mour
    -0.69
    ittää
    -0.69
    POSITIVE LOGITS
     subjective
    5.06
     subjectivity
    3.88
     субъек
    3.50
     subjek
    3.36
     subjec
    3.33
     subje
    2.72
    jective
    2.64
     sogget
    2.64
     SUBJECT
    2.39
     objective
    2.30
    Activations Density 0.095%

    No Known Activations