© 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. 110744
    Prev
    Next
    INDEX
    Explanations

    financial metrics

    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
    Kiedy
    -0.84
    onik
    -0.82
     Disciples
    -0.77
    碎片
    -0.76
     pension
    -0.73
     Collateral
    -0.73
    うた
    -0.72
    Zapraszamy
    -0.72
    fondos
    -0.71
    泰
    -0.71
    POSITIVE LOGITS
     flywheel
    0.94
     jaką
    0.89
    vertisers
    0.89
     deceler
    0.85
     advertisers
    0.85
     lifetime
    0.82
    gna
    0.78
    طلحات
    0.77
     cohorts
    0.77
     getUser
    0.77
    Activations Density 0.013%

    No Known Activations