© 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. 220281
    Prev
    Next
    INDEX
    Explanations

    disclosing personal information

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

    place and movement

    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
     Admission
    0.47
     Directions
    0.46
     Proposed
    0.45
     References
    0.45
     Expenditures
    0.44
     Luật
    0.44
     Admissions
    0.43
     ₽
    0.43
     Zoning
    0.43
     Products
    0.43
    POSITIVE LOGITS
     detoxification
    0.46
    的重要性
    0.46
     immunoblot
    0.45
     cytotoxicity
    0.42
     mikro
    0.42
     microstructure
    0.42
    では
    0.41
     myosin
    0.41
     pulau
    0.41
     waar
    0.40
    Activations Density 0.002%

    No Known Activations