© 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. 34-GEMMASCOPE-RES-131K
    7. 66418
    Prev
    Next
    INDEX
    Explanations

    JB or JabJab or Jabouin

    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
    rät
    -0.81
    Przed
    -0.79
     sq
    -0.75
    مكان
    -0.75
    grund
    -0.75
    Те
    -0.74
    hyper
    -0.73
    Den
    -0.73
    wait
    -0.73
    Кон
    -0.72
    POSITIVE LOGITS
     Wechsel
    0.77
    illent
    0.74
    Externé
    0.71
    спомина
    0.69
    Eck
    0.68
    ਲਾ
    0.68
    tisti
    0.66
    Comparisons
    0.65
    しっかりと
    0.65
    大多数
    0.65
    Activations Density 0.022%

    No Known Activations