© 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. 83997
    Prev
    Next
    INDEX
    Explanations

    document titles and categories

    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
    mäßigen
    -0.82
    Учитель
    -0.80
    wakili
    -0.73
    BLAST
    -0.73
     pseudos
    -0.72
     Overrides
    -0.71
    isola
    -0.71
    junge
    -0.71
    Ав
    -0.71
    ventana
    -0.70
    POSITIVE LOGITS
     referral
    0.77
    earch
    0.73
    Start
    0.73
    odle
    0.72
    hyrchwyd
    0.68
     poorest
    0.67
    人参
    0.67
    bek
    0.66
     Perkins
    0.66
     будет
    0.65
    Activations Density 0.049%

    No Known Activations