© 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. 80937
    Prev
    Next
    INDEX
    Explanations

    parameter names and return types

    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
     every
    -1.03
     horrific
    -1.00
     conseguido
    -0.96
     början
    -0.95
    Gotham
    -0.94
     coupled
    -0.93
    Kaynak
    -0.93
    PlainText
    -0.93
     helg
    -0.93
     venturing
    -0.93
    POSITIVE LOGITS
     The
    1.30
    cency
    1.09
     It
    1.09
    usermodel
    1.08
    The
    1.03
     This
    0.97
    LogFactory
    0.95
    瞅
    0.94
    増加
    0.94
     novamente
    0.92
    Activations Density 0.016%

    No Known Activations