© 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. 17332
    Prev
    Next
    INDEX
    Explanations

    use less

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

    functions and limitations

    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
     нарушения
    0.46
     Ξ
    0.45
     ভিক্ষ
    0.44
     Δ
    0.43
    規
    0.43
    禍
    0.42
    ництва
    0.41
    ственности
    0.40
     лиш
    0.40
     deadlock
    0.39
    POSITIVE LOGITS
    की
    0.46
    จัย
    0.44
    Republic
    0.43
    ኻ
    0.42
     caer
    0.42
     soutenir
    0.42
    是非常
    0.42
    íqu
    0.41
    ᕝ
    0.41
    পাকিস্ত
    0.41
    Activations Density 0.000%

    No Known Activations