© 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. 111728
    Prev
    Next
    INDEX
    Explanations

    asof

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

    options or questions

    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
    ("/{
    0.45
     Noether
    0.42
     weep
    0.42
     Colts
    0.42
     "/",
    0.42
     hemisph
    0.42
     exhibiting
    0.41
     Nxb
    0.41
     sweating
    0.41
     noble
    0.40
    POSITIVE LOGITS
    ១
    0.50
    គ្រ
    0.50
    üman
    0.47
    ние
    0.45
    stå
    0.44
    सुन
    0.43
     शेड्यूल
    0.43
    dür
    0.42
    NING
    0.42
    人人
    0.42
    Activations Density 0.000%

    No Known Activations