© 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. 84709
    Prev
    Next
    INDEX
    Explanations

    international controversy

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

    Tyre sole

    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
    tern
    0.42
     infringed
    0.42
     حتی
    0.41
    ↵
    0.41
     навіть
    0.40
    proposed
    0.40
    repet
    0.39
    ່ມ
    0.39
     आगामी
    0.38
    rene
    0.38
    POSITIVE LOGITS
    摟
    0.44
     Labrenzia
    0.44
    وم
    0.43
    葶
    0.43
    の高い
    0.42
    ോക
    0.42
    粛
    0.42
    హి
    0.42
     Divided
    0.41
    地产
    0.41
    Activations Density 0.001%

    No Known Activations