© 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. 22-GEMMASCOPE-RES-131K
    7. 84539
    Prev
    Next
    INDEX
    Explanations

    starts of descriptive phrases

    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_22/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
     believes
    -0.97
     auxiliar
    -0.96
     aeron
    -0.96
     anum
    -0.95
     diras
    -0.93
    믿
    -0.91
     precau
    -0.90
     September
    -0.90
    ských
    -0.89
     believe
    -0.88
    POSITIVE LOGITS
     is
    1.19
     also
    1.13
     acht
    1.11
     també
    1.09
     can
    0.99
     także
    0.98
    u
    0.94
     cũng
    0.92
     stück
    0.92
     passend
    0.90
    Activations Density 0.000%

    No Known Activations