© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91786
    Prev
    Next
    INDEX
    Explanations

    sections and headers

    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
     their
    -0.91
     even
    -0.87
     欣赏
    -0.84
    鵟
    -0.82
    дні
    -0.82
     any
    -0.81
    chappen
    -0.81
    natured
    -0.81
     viera
    -0.81
     unrelenting
    -0.79
    POSITIVE LOGITS
     nin
    0.94
    今から
    0.93
     SEVEN
    0.88
     zen
    0.88
     richer
    0.87
     pyta
    0.86
    beginning
    0.84
    hman
    0.84
    zumaki
    0.84
    ラー
    0.82
    Activations Density 0.000%

    No Known Activations