© 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. 7272
    Prev
    Next
    INDEX
    Explanations

    myth, mythology, mythical

    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
     он
    -0.88
    oprecipitation
    -0.88
     включая
    -0.84
    postIndex
    -0.84
    高校
    -0.80
    imgdir
    -0.80
    ituitary
    -0.80
    idends
    -0.79
     tumors
    -0.79
    salms
    -0.77
    POSITIVE LOGITS
    myth
    1.14
     Myth
    1.06
    ical
    1.05
    ologies
    1.03
    olog
    1.00
    Myth
    0.95
    making
    0.93
    ically
    0.92
    Inaug
    0.89
    MAKING
    0.89
    Activations Density 0.013%

    No Known Activations