© 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. 40823
    Prev
    Next
    INDEX
    Explanations

    references, claim, section, China

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

    becoming prevalent

    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
    hor
    0.46
     giai
    0.45
     Ronald
    0.43
    ertype
    0.43
    🆗
    0.43
    感受
    0.42
    骅
    0.41
    ერ
    0.41
     vond
    0.41
     james
    0.41
    POSITIVE LOGITS
    ibm
    0.47
     आसपास
    0.45
    minipage
    0.45
    ịn
    0.44
    यदि
    0.44
    IS
    0.44
     ಏಕೆಂದರೆ
    0.44
     Condensed
    0.43
    ૧
    0.43
     внимания
    0.42
    Activations Density 0.001%

    No Known Activations