© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29188
    Prev
    Next
    INDEX
    Explanations

    Figure and Table references

    np_acts-logits-general · gemini-2.5-flash-lite

    table summarizing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     topography
    0.50
    叧
    0.47
     abdom
    0.46
     subcut
    0.46
     femora
    0.45
     absc
    0.45
     spectroscopy
    0.44
     momenta
    0.42
     abyss
    0.42
     parenchyma
    0.42
    POSITIVE LOGITS
    Captain
    0.50
    멋
    0.49
    helle
    0.49
    Helping
    0.48
     读取
    0.46
    hena
    0.45
    نمية
    0.45
    Fuente
    0.44
    랫폼
    0.43
     giúp
    0.43
    Activations Density 0.012%

    No Known Activations