© 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. 90149
    Prev
    Next
    INDEX
    Explanations

    statistical mechanics and strong coupling

    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
     fairly
    -1.05
     their
    -0.96
     commonly
    -0.96
     graphically
    -0.93
     most
    -0.91
     while
    -0.90
     meticulous
    -0.89
     when
    -0.88
     both
    -0.85
     medical
    -0.85
    POSITIVE LOGITS
     هناك
    1.13
    AndEndTag
    1.03
    wania
    0.98
    읗
    0.98
    NgModule
    0.95
     Kwan
    0.93
    ASE
    0.93
    atiker
    0.92
    estyle
    0.92
    íc
    0.92
    Activations Density 0.001%

    No Known Activations